© 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. 94645
    Prev
    Next
    INDEX
    Explanations

    code snippets or documents

    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
    itri
    -0.79
    fjspx
    -0.69
    ParallelGroup
    -0.53
     createSlice
    -0.52
     disambiguazione
    -0.50
    CloseOperation
    -0.49
    parsedMessage
    -0.49
    enseits
    -0.49
    рез
    -0.48
    DllImport
    -0.48
    POSITIVE LOGITS
     незавершена
    0.92
    basicConfig
    0.80
    Boletín
    0.59
     ValueError
    0.56
    RUnlock
    0.56
    //*/
    0.55
    Telefax
    0.55
    //});
    0.55
    writeField
    0.55
     Administrators
    0.54
    Activations Density 2.133%

    No Known Activations