© 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. 22-RES-MATRYOSHKA-DC
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Према
    -0.53
    Abit
    -0.45
     yii
    -0.45
    .*")]
    -0.45
     Carey
    -0.44
    avat
    -0.44
     bağlantılar
    -0.43
    рое
    -0.42
    fire
    -0.42
    meler
    -0.41
    POSITIVE LOGITS
     DX
    0.70
     SqlCommand
    0.64
    UnknownFieldSet
    0.63
     ThemeData
    0.60
    ValueStyle
    0.60
     mtrl
    0.58
    клопе
    0.58
     Shand
    0.58
     Shock
    0.57
     jadx
    0.57
    Activations Density 0.012%

    No Known Activations