© 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. 4-CLT-HP
    7. 979
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.90
    WriteBarrier
    -0.84
    tagHelperRunner
    -0.80
    ."],
    -0.78
    mergeFrom
    -0.77
    istoitu
    -0.76
    ]));
    -0.76
     createSlice
    -0.73
    #+#
    -0.73
     كومونز
    -0.73
    POSITIVE LOGITS
    ?
    0.75
     it
    0.71
     that
    0.65
     this
    0.61
    ??
    0.59
     your
    0.58
    ???
    0.57
    ？
    0.50
     saying
    0.50
    ?????
    0.49
    Activations Density 0.003%

    No Known Activations