© 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. 18-RES-MATRYOSHKA-DC
    7. 815
    Prev
    Next
    INDEX
    Explanations

    parts of a computer log

    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.18.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.18.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
    </i>
    -1.07
    </b>
    -0.69
    <i>
    -0.56
    <b>
    -0.51
    </u>
    -0.51
     ${\
    -0.45
    &#
    -0.44
    _
    -0.43
    estris
    -0.43
    </code>
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    1.11
     nahilalakip
    0.94
    MigrationBuilder
    0.93
    /**
    0.89
    SourceChecksum
    0.88
    DoubleQuotes
    0.88
    AccessorTable
    0.87
    )";
    0.87
    adaptiveStyles
    0.86
     """
    0.86
    Activations Density 1.664%

    No Known Activations