© 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. 5524
    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
    WebVitals
    -0.83
    LookAnd
    -0.75
     resourceCulture
    -0.69
    createCanvas
    -0.69
     OnInit
    -0.66
    IBarButtonItem
    -0.65
    TestBed
    -0.63
     supuestamente
    -0.63
    出版年
    -0.61
    DockStyle
    -0.60
    POSITIVE LOGITS
    interopRequire
    0.52
     Pristupljeno
    0.50
     Repeat
    0.49
     riuscito
    0.46
     Very
    0.45
     Abuse
    0.45
     Treating
    0.44
     incendios
    0.44
     serez
    0.44
     Longer
    0.44
    Activations Density 0.000%

    No Known Activations