© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11918
    Prev
    Next
    INDEX
    Explanations

    potential keywords related to political controversy and news events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.11
    0.3%
    1150
    +0.11
    0.3%
    1919
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.11
    0.07
    862
    +0.11
    0.03
    513
    +0.10
    0.04
    Negative Logits
     seaborn
    -0.45
    isbol
    -0.44
    Elő
    -0.44
     Direito
    -0.43
     Gestão
    -0.43
     fotovolta
    -0.43
     trám
    -0.43
     BioLib
    -0.42
     ekos
    -0.42
     Parfum
    -0.41
    POSITIVE LOGITS
     intersper
    0.67
     overcrow
    0.57
     gratify
    0.57
     depic
    0.57
     resemb
    0.56
     Personne
    0.56
     quitted
    0.56
     guarante
    0.54
     McInt
    0.54
     חיצוניים
    0.53
    Activations Density 0.546%

    No Known Activations