© 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. 0-CLT-HP
    7. 93433
    Prev
    Next
    INDEX
    Explanations

    German

    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
     hab
    -0.91
     ExecuteAsync
    -0.82
    +#+#
    -0.67
     BoxDecoration
    -0.63
    DoubleQuotes
    -0.63
     Chwiliwch
    -0.60
     CreateTagHelper
    -0.59
     समीक्षाओं
    -0.59
     opérés
    -0.58
     समीक्षाएं
    -0.57
    POSITIVE LOGITS
    <bos>
    0.46
    doj
    0.45
    medriver
    0.44
     getP
    0.44
    ilak
    0.43
     Hilde
    0.43
     históricas
    0.42
    pch
    0.41
     trekken
    0.41
    ilis
    0.41
    Activations Density 0.452%

    No Known Activations