© 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. 5213
    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
    Flop
    -0.46
    ,
    -0.42
    Drip
    -0.39
    up
    -0.39
    Onion
    -0.38
     Drip
    -0.38
    teal
    -0.35
     up
    -0.34
     i
    -0.34
    PrototypeOf
    -0.34
    POSITIVE LOGITS
    StoryboardSegue
    0.98
     виправивши
    0.80
    CodeAttribute
    0.76
    >{@
    0.75
     Shakspeare
    0.74
     سكانية
    0.74
    ientí
    0.73
    Demografie
    0.72
    DockStyle
    0.72
    Diwedd
    0.72
    Activations Density 0.002%

    No Known Activations