© 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. 350
    Prev
    Next
    INDEX
    Explanations

    caused/induced

    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
     myſelf
    -1.00
     itſelf
    -1.00
     raiſ
    -0.96
     Jefus
    -0.92
     becauſe
    -0.91
     Efq
    -0.90
    Hochspringen
    -0.89
     cauſe
    -0.84
     himſelf
    -0.83
     Monfieur
    -0.83
    POSITIVE LOGITS
     to
    1.02
     To
    0.80
    To
    0.66
     TO
    0.63
    ToInt
    0.61
    to
    0.56
     לב
    0.52
     kepada
    0.48
    ato
    0.47
    cto
    0.47
    Activations Density 0.003%

    No Known Activations