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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8869
    Prev
    Next
    INDEX
    Explanations

    experimental testing and hypotheses related to various subjects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kare
    -0.70
     Kome
    -0.65
    Попис
    -0.64
    ations
    -0.63
     Nc
    -0.60
    tive
    -0.60
    `),
    -0.60
    withstanding
    -0.60
    regate
    -0.60
     Nid
    -0.60
    POSITIVE LOGITS
    ReusableCell
    0.72
    tymologie
    0.71
    setOnAction
    0.68
    contentLoaded
    0.67
    jsonwebtoken
    0.67
    AsUp
    0.66
    liothèque
    0.63
    gridx
    0.63
    ictwa
    0.61
     mAdapter
    0.60
    Activations Density 0.021%

    No Known Activations