© 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. 42177
    Prev
    Next
    INDEX
    Explanations

    Dates and events

    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
    󠁿
    -0.76
     متعلقه
    -0.73
    protoimpl
    -0.71
    Tikang
    -0.68
    gonic
    -0.65
     Cæsar
    -0.63
     Roskov
    -0.63
    AndEndTag
    -0.63
    hdashline
    -0.63
     câte
    -0.63
    POSITIVE LOGITS
     يتيمه
    0.56
     ब्रेकडाउन
    0.46
    twimg
    0.45
    外部リンク
    0.42
     fin
    0.42
     dele
    0.42
     maga
    0.41
    Показать
    0.40
     ActivatedRoute
    0.39
    珠
    0.39
    Activations Density 0.055%

    No Known Activations