© 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. 20-CLT-HP
    7. 77810
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ingly
    -0.95
     myſelf
    -0.93
    inq
    -0.88
     Monfieur
    -0.87
     Theſe
    -0.85
    ^(@)
    -0.85
    eing
    -0.85
     ProtoMessage
    -0.84
     незавершена
    -0.84
    ored
    -0.84
    POSITIVE LOGITS
    ハ
    0.33
    ka
    0.32
    no
    0.31
     estavam
    0.30
     estés
    0.29
    To
    0.28
    N
    0.28
    not
    0.28
     hogares
    0.28
     dalamnya
    0.27
    Activations Density 0.000%

    No Known Activations