© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4191
    Prev
    Next
    INDEX
    Explanations

    additions

    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
    both
    -0.60
     ziren
    -0.56
    others
    -0.54
     bParam
    -0.54
    ="#"><
    -0.52
    Filmografie
    -0.52
    Opin
    -0.51
    '=>'
    -0.50
    AnchorStyles
    -0.50
    ']==
    -0.49
    POSITIVE LOGITS
     benefit
    0.64
     voordeel
    0.63
     advantage
    0.63
     ModelExpression
    0.62
    σιμοποι
    0.61
     fact
    0.60
     незавершена
    0.60
     feature
    0.58
    getResource
    0.57
    WillAppear
    0.57
    Activations Density 0.004%

    No Known Activations