© 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. 14775
    Prev
    Next
    INDEX
    Explanations

    legal/formal 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
    NR
    -0.67
     of
    -0.39
    ئيس
    -0.36
     kapcsolat
    -0.36
    nr
    -0.36
     aprobado
    -0.35
    canActivate
    -0.34
    ppur
    -0.34
     tou
    -0.34
    quiti
    -0.34
    POSITIVE LOGITS
    +#+#
    1.05
    BeginContext
    0.80
    aarrggbb
    0.71
     الاطلاع
    0.71
    awtextra
    0.69
     Majefty
    0.69
    mergeFrom
    0.69
     дописавши
    0.66
    IMENTAL
    0.65
     Jefus
    0.65
    Activations Density 0.017%

    No Known Activations