© 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. 1-CLT-HP
    7. 10133
    Prev
    Next
    INDEX
    Explanations

    Acronyms

    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
    TagMode
    -0.91
     насељу
    -0.83
    Personendaten
    -0.79
    ConstraintMaker
    -0.78
    ValueStyle
    -0.73
    клопе
    -0.73
    SequentialGroup
    -0.73
    boretum
    -0.71
    awaiter
    -0.71
    hatenablog
    -0.70
    POSITIVE LOGITS
     hay
    0.48
    dhury
    0.39
    ffo
    0.39
    انيف
    0.37
     del
    0.35
     Hay
    0.35
     X
    0.35
    chau
    0.34
    семь
    0.34
     f
    0.34
    Activations Density 0.018%

    No Known Activations