© 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. 0-CLT-HP
    7. 42800
    Prev
    Next
    INDEX
    Explanations

    families and children

    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
     "..\..\
    -0.66
     "..\..\..\
    -0.66
     ExecuteAsync
    -0.54
    setSuccess
    -0.51
    (['/
    -0.50
    //});
    -0.49
     ['./
    -0.49
    duğu
    -0.48
    %"),
    -0.47
    بيت
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.86
    WithIOException
    0.72
     متعلقه
    0.63
    rungsseite
    0.61
    ValueStyle
    0.61
    DotNetBar
    0.60
    styleType
    0.59
     دیکھیے
    0.58
    <bos>
    0.56
     الرياضيه
    0.56
    Activations Density 0.074%

    No Known Activations