© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 775
    Prev
    Next
    INDEX
    Explanations

    negative legal or medical claims.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    GraphicsUnit
    -0.79
    ⓧ
    -0.79
     habet
    -0.76
     يتيمه
    -0.71
     quæ
    -0.68
     auffi
    -0.68
     uſe
    -0.68
     définiti
    -0.68
     fédé
    -0.67
    principalColumn
    -0.66
    POSITIVE LOGITS
     fall
    0.65
     amount
    0.59
    Amount
    0.57
     falls
    0.56
     Fall
    0.56
     CONST
    0.55
     Amount
    0.54
     constitute
    0.53
    amount
    0.51
     constituted
    0.51
    Activations Density 0.740%

    No Known Activations