© 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. 0-CLT-HP
    7. 94931
    Prev
    Next
    INDEX
    Explanations

    BC DC English

    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
     
    -1.03
     English
    -0.88
     a
    -0.85
     L
    -0.84
     R
    -0.84
     I
    -0.82
     P
    -0.80
     (
    -0.79
     M
    -0.79
     C
    -0.78
    POSITIVE LOGITS
     Efq
    2.19
     itſelf
    2.19
     myſelf
    2.13
     Monfieur
    2.02
     Theſe
    1.95
     Jefus
    1.95
     Houſe
    1.92
     themſelves
    1.91
     ―――――
    1.91
     raiſ
    1.88
    Activations Density 0.281%

    No Known Activations