© 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. 7409
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism and social movements

    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
    1013
    +0.11
    0.3%
    562
    +0.11
    0.3%
    1392
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.11
    0.05
    562
    +0.11
    0.04
    353
    +0.10
    0.04
    Negative Logits
    idenav
    -0.51
     iub
    -0.49
    queeze
    -0.47
     simplu
    -0.47
     katkıda
    -0.46
    ariConfig
    -0.46
    lalom
    -0.44
     beelden
    -0.42
     acestea
    -0.40
    érience
    -0.40
    POSITIVE LOGITS
     ejus
    0.80
     tamen
    0.74
     Cæ
    0.70
     buc
    0.70
     tibi
    0.67
     potest
    0.67
     magis
    0.67
     poff
    0.67
    €/
    0.67
     nomine
    0.66
    Activations Density 0.234%

    No Known Activations