© 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. 3-RES-MATRYOSHKA-DC
    7. 1737
    Prev
    Next
    INDEX
    Explanations

    the word "of" that is often part of a longer phrase

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yargs
    -0.54
     Pram
    -0.50
    secta
    -0.49
    ticum
    -0.48
     gravity
    -0.46
    merzen
    -0.45
     gently
    -0.45
    chodzą
    -0.44
    )))));
    -0.44
    ủa
    -0.44
    POSITIVE LOGITS
    fjspx
    0.81
    LookAnd
    0.71
    toMatchSnapshot
    0.69
     Efq
    0.66
    aarrggbb
    0.66
    ieuses
    0.66
     مشين
    0.65
    ValueStyle
    0.63
    Composable
    0.62
     ffilmiau
    0.62
    Activations Density 0.790%

    No Known Activations