© 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. 42319
    Prev
    Next
    INDEX
    Explanations

    reporting verbs

    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
    Personensuche
    -0.90
     him
    -0.87
     honom
    -0.86
     Egli
    -0.84
    ThroughAttribute
    -0.82
     hänen
    -0.81
    новниш
    -0.79
     hän
    -0.78
     tiegħ
    -0.77
    His
    -0.76
    POSITIVE LOGITS
     our
    0.72
     their
    0.62
    <bos>
    0.60
     the
    0.57
     an
    0.55
     a
    0.49
     s
    0.47
     '
    0.47
     host
    0.47
     n
    0.47
    Activations Density 0.039%

    No Known Activations