© 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. 92762
    Prev
    Next
    INDEX
    Explanations

    scale

    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
    matchCondition
    -0.65
    LEEP
    -0.65
     فريبيس
    -0.56
    complexContent
    -0.55
    CodedInputStream
    -0.54
    zep
    -0.51
    хьтан
    -0.51
    restes
    -0.50
     apport
    -0.50
     Caucus
    -0.50
    POSITIVE LOGITS
     of
    0.68
     for
    0.66
    <bos>
    0.52
    adaptiveStyles
    0.51
    IsContent
    0.50
     developed
    0.50
    CppCodeGen
    0.49
    Developed
    0.47
     विश्वसनीयता
    0.46
    RenderAtEndOf
    0.46
    Activations Density 0.001%

    No Known Activations