© 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. 633
    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
    enumi
    -0.69
    '][]
    -0.48
    '<
    -0.43
    KURZBESCHREIBUNG
    -0.43
    "+
    -0.42
    AddTagHelper
    -0.41
    qq
    -0.41
    enumii
    -0.40
    iestety
    -0.40
    AndEndTag
    -0.40
    POSITIVE LOGITS
     résister
    0.61
    umumkan
    0.59
    keits
    0.57
    geschlossen
    0.56
     résistant
    0.56
     résistance
    0.55
    Vidite
    0.55
    volves
    0.54
    gimento
    0.54
     onCreateView
    0.54
    Activations Density 0.005%

    No Known Activations