© 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. 5-CLT-HP
    7. 91815
    Prev
    Next
    INDEX
    Explanations

    ities

    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
     समीक्षक
    -0.60
    Tracce
    -0.59
     "!
    -0.54
    ViewChild
    -0.53
     $"
    -0.51
     Cataloging
    -0.50
    WriteAttribute
    -0.49
     "..
    -0.48
    "…
    -0.48
     "...
    -0.47
    POSITIVE LOGITS
     magnética
    0.63
     FetchType
    0.61
    Personensuche
    0.59
     виправивши
    0.58
    WithIOException
    0.56
    دانشنامهٔ
    0.56
     مشين
    0.56
     magnético
    0.55
    ΩΝ
    0.54
    ]--;
    0.54
    Activations Density 0.002%

    No Known Activations