© 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. 2442
    Prev
    Next
    INDEX
    Explanations

    the beginning of a sentence explaining how to retrieve a license

    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
    unknownFields
    -0.58
    UnknownFieldSet
    -0.48
    FieldSet
    -0.45
    ұл
    -0.42
    setViewName
    -0.42
     minori
    -0.42
    ونده
    -0.42
     redondo
    -0.42
     فريبيس
    -0.41
     vedi
    -0.41
    POSITIVE LOGITS
     copy
    1.10
     copies
    0.92
    copy
    0.89
     Copy
    0.82
     Copies
    0.79
    Copies
    0.79
    Copy
    0.79
     copie
    0.77
     COPY
    0.76
    COPY
    0.73
    Activations Density 0.010%

    No Known Activations