© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1761
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    EDEFAULT
    -0.95
    tvguidetime
    -0.74
    HostException
    -0.73
    ResponseWriter
    -0.71
    providedIn
    -0.68
    ReusableCell
    -0.68
     Vichy
    -0.67
    EndInit
    -0.67
    Hochspringen
    -0.65
    idopsis
    -0.64
    POSITIVE LOGITS
     box
    0.46
     al
    0.40
     Box
    0.38
    neiden
    0.38
     fre
    0.38
     kee
    0.37
    цкого
    0.35
    ();)
    0.35
    قایناقلار
    0.35
    ,
    0.35
    Activations Density 0.002%

    No Known Activations