© 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. 1-CLT-HP
    7. 11366
    Prev
    Next
    INDEX
    Explanations

    new

    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
    AutoScaleMode
    -0.58
    viewDidLoad
    -0.56
    cupertino
    -0.56
     AttributeSet
    -0.55
    principalColumn
    -0.54
     Вікі
    -0.52
    UpInside
    -0.51
    Sauce
    -0.49
     TextAppearance
    -0.48
    ocats
    -0.48
    POSITIVE LOGITS
     تانيه
    0.60
    новниш
    0.56
    NUMX
    0.56
    basicConfig
    0.50
    noticia
    0.48
    }$}
    0.46
    ernoo
    0.46
    esterday
    0.46
     Poincar
    0.46
    DoubleQuotes
    0.44
    Activations Density 0.011%

    No Known Activations