© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
    dymyr
    -0.70
    ViewFeatures
    -0.57
    InputBorder
    -0.55
    帖最后由
    -0.54
     htons
    -0.52
     slike
    -0.52
    endpush
    -0.52
    Nih
    -0.52
    DebuggerStep
    -0.52
    namics
    -0.52
    POSITIVE LOGITS
     \
    0.99
     very
    0.58
     CGRectMake
    0.52
    very
    0.51
    VERY
    0.49
    LLocation
    0.49
    úrese
    0.48
    FirstResponder
    0.48
     Voor
    0.48
     Very
    0.48
    Activations Density 0.138%

    No Known Activations