© 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. 4-CLT-HP
    7. 245
    Prev
    Next
    INDEX
    Explanations

    research and reports

    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
     themſelves
    -0.85
    EDEFAULT
    -0.85
     myſelf
    -0.85
     itſelf
    -0.85
     Monfieur
    -0.80
     himſelf
    -0.77
     houſe
    -0.70
     propOrder
    -0.70
     Eſ
    -0.69
     whoſe
    -0.69
    POSITIVE LOGITS
    ContentAsync
    0.62
    aarrggbb
    0.60
    TargetException
    0.48
    liothèque
    0.47
    SequentialGroup
    0.44
     etc
    0.43
    ArgsConstructor
    0.43
    ्त
    0.42
     Type
    0.42
     “
    0.41
    Activations Density 0.137%

    No Known Activations