© 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. 564
    Prev
    Next
    INDEX
    Explanations

    :

    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
     from
    -0.49
     arising
    -0.49
     aboard
    -0.47
     or
    -0.47
     represents
    -0.46
     arises
    -0.45
     originating
    -0.45
     אומר
    -0.45
     borne
    -0.45
     Especific
    -0.45
    POSITIVE LOGITS
     kasarigan
    0.80
    Rüyada
    0.79
     You
    0.79
    InvalidProtocol
    0.76
    SourceChecksum
    0.73
     الحره
    0.70
     فريبيس
    0.67
    Personensuche
    0.64
     My
    0.63
     صوتيه
    0.63
    Activations Density 0.001%

    No Known Activations