© 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. 5-CLT-HP
    7. 91707
    Prev
    Next
    INDEX
    Explanations

    '

    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
    ῖν
    -0.47
    IsContent
    -0.46
    Anyway
    -0.43
     hjer
    -0.42
    ỏa
    -0.40
     quedarse
    -0.40
     cynicism
    -0.39
    InitVars
    -0.39
    lový
    -0.38
    šanu
    -0.38
    POSITIVE LOGITS
    MemoryWarning
    0.80
    日閲覧
    0.73
    مصادر
    0.73
    UrlResolution
    0.69
     magasiner
    0.69
    )++;
    0.68
    addPreferredGap
    0.65
    ]--;
    0.65
    TextBoxColumn
    0.64
    最快更新
    0.63
    Activations Density 0.000%

    No Known Activations