© 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. 5-CLT-HP
    7. 5898
    Prev
    Next
    INDEX
    Explanations

    Numbers and people

    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
    %")
    -0.58
    ">)</
    -0.47
    ,**
    -0.46
     Vict
    -0.46
     onCreateView
    -0.45
    DoubleQuotes
    -0.44
     كومونز
    -0.44
     —
    -0.44
    relse
    -0.44
    ErrorListener
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.83
     ModelExpression
    0.76
     ComVisible
    0.75
    blurRadius
    0.71
    UniformLocation
    0.69
    kháu
    0.67
    OGND
    0.67
     AssemblyProduct
    0.66
     AssemblyVersion
    0.65
    AndroidJUnit
    0.63
    Activations Density 0.002%

    No Known Activations