© 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. 5-CLT-HP
    7. 93179
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    AndEndTag
    -0.87
    <bos>
    -0.85
     مشين
    -0.84
    IntoConstraints
    -0.80
    例文帳に追加
    -0.75
    LookAnd
    -0.72
    awtextra
    -0.71
    
    -0.69
     consultato
    -0.69
    ModelAdmin
    -0.69
    POSITIVE LOGITS
    Everything
    0.37
     
    0.37
     cópia
    0.37
     you
    0.36
    ziert
    0.35
    찮
    0.35
     Everything
    0.35
     You
    0.34
     GOOD
    0.34
    lapsingToolbar
    0.33
    Activations Density 0.001%

    No Known Activations