© 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. 11852
    Prev
    Next
    INDEX
    Explanations

    mentions of the Taliban

    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
    421
    +0.15
    0.6%
    1984
    +0.12
    0.5%
    1068
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.05
    1177
    +0.12
    0.02
    1984
    +0.12
    0.04
    Negative Logits
     hoga
    -0.57
     magnes
    -0.57
    Trimethyl
    -0.51
     Buff
    -0.50
     abnorm
    -0.49
     gneiss
    -0.49
    ethene
    -0.49
    Perché
    -0.49
    IsContent
    -0.48
    loroethene
    -0.47
    POSITIVE LOGITS
     Tal
    0.62
     Taliban
    0.61
     Româ
    0.61
     Docteur
    0.59
     Secrétaire
    0.58
    Tal
    0.54
     Leurs
    0.54
     BT
    0.49
     TAL
    0.48
     chevalier
    0.47
    Activations Density 0.303%

    No Known Activations