© 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. 10223
    Prev
    Next
    INDEX
    Explanations

    book references

    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
    +:+
    -0.81
     وتسجيلات
    -0.64
     pinulongan
    -0.59
     dàng
    -0.58
    Халык
    -0.54
    vábbi
    -0.54
    最快更新
    -0.53
    uffle
    -0.53
     @}
    -0.52
    tvguidetime
    -0.52
    POSITIVE LOGITS
    bootstrapcdn
    0.52
    Filmografie
    0.49
     CURIAM
    0.45
     buck
    0.44
     hooves
    0.43
    oléon
    0.43
     plati
    0.41
     Tacitus
    0.40
     verme
    0.40
     saint
    0.40
    Activations Density 0.002%

    No Known Activations