© 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. 4-CLT-HP
    7. 461
    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
    protoimpl
    -0.75
     ویکی‌پدی
    -0.74
     Wikimedijinoj
    -0.68
    NameInMap
    -0.68
    ReusableCell
    -0.66
     nahilalakip
    -0.66
    setVerticalGroup
    -0.65
    seamless
    -0.65
    WebVitals
    -0.64
    ].)
    -0.63
    POSITIVE LOGITS
    posób
    0.53
     credere
    0.48
    grano
    0.48
     Hypothesis
    0.47
     keterampilan
    0.47
     secondaires
    0.46
     Barkley
    0.46
     maybe
    0.44
     magari
    0.44
    Géographie
    0.44
    Activations Density 0.008%

    No Known Activations