© 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. 10363
    Prev
    Next
    INDEX
    Explanations

    tase

    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
     Efq
    -0.85
     doInBackground
    -0.84
    abestanden
    -0.82
    ^(@)
    -0.81
     disponibilités
    -0.78
    GEBURTSDATUM
    -0.71
     HasFactory
    -0.70
     métallique
    -0.67
    NUMX
    -0.67
     MyBatis
    -0.67
    POSITIVE LOGITS
     an
    0.56
     to
    0.55
    an
    0.54
     a
    0.52
    SequentialGroup
    0.50
    List
    0.47
     hit
    0.47
    AnchorStyles
    0.47
     generous
    0.45
    M
    0.44
    Activations Density 0.043%

    No Known Activations