© 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. 42715
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
     Di
    -0.73
     Katz
    -0.67
     a
    -0.63
     ca
    -0.63
     cu
    -0.63
     the
    -0.61
     of
    -0.54
     di
    -0.53
     Cu
    -0.53
     arrived
    -0.52
    POSITIVE LOGITS
     himſelf
    0.92
     Efq
    0.88
     unſ
    0.86
     تانيه
    0.86
     Monfieur
    0.85
     themſelves
    0.84
     myſelf
    0.84
     Eſ
    0.82
     houſe
    0.82
     ſch
    0.81
    Activations Density 0.265%

    No Known Activations