© 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. 91765
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Hochspringen
    -0.71
    ंदीखरीदारी
    -0.68
    ագրություններ
    -0.65
     चीज़ों
    -0.65
     sẻ
    -0.65
    principalColumn
    -0.65
     Administrativna
    -0.63
    GEBURTSDATUM
    -0.63
     onBind
    -0.62
     ModelExpression
    -0.62
    POSITIVE LOGITS
     are
    0.75
    /
    0.75
     is
    0.67
     occurs
    0.62
     can
    0.61
     was
    0.60
     arises
    0.60
     has
    0.59
     varies
    0.57
     occurred
    0.56
    Activations Density 0.001%

    No Known Activations