© 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. 98268
    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
    .
    -0.71
    ...
    -0.70
    -0.67
    LabelTagHelper
    -0.60
    …
    -0.59
    \\
    -0.58
    (
    -0.55
    ,
    -0.54
    ↵
    -0.54
    ?
    -0.54
    POSITIVE LOGITS
    5
    0.81
    8
    0.78
    6
    0.74
    7
    0.74
     purpoſe
    0.73
    9
    0.73
    4
    0.73
    3
    0.72
     ſy
    0.70
     myſelf
    0.69
    Activations Density 0.007%
    No Known Activations