© 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. 759
    Prev
    Next
    INDEX
    Explanations

    the

    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
     createState
    -0.70
     consultato
    -0.69
    +#+#
    -0.68
    SequentialGroup
    -0.64
     typelib
    -0.62
     TType
    -0.59
    tslib
    -0.59
     mxArray
    -0.56
    oneofs
    -0.56
    出版年
    -0.56
    POSITIVE LOGITS
     myſelf
    0.59
     pleaſure
    0.56
     itſelf
    0.56
     houſe
    0.56
     ſeveral
    0.55
     faſt
    0.55
     ſche
    0.54
     fubject
    0.52
     purpoſe
    0.52
     Jefus
    0.52
    Activations Density 0.004%

    No Known Activations