© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1185
    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
     lido
    -0.50
    localObject
    -0.50
     sez
    -0.49
     coö
    -0.49
     canst
    -0.49
     tyme
    -0.49
     crows
    -0.48
     diocese
    -0.48
     財布
    -0.48
     gardener
    -0.48
    POSITIVE LOGITS
     AssemblyCulture
    0.94
    StoryboardSegue
    0.91
     CreateTagHelper
    0.88
     The
    0.63
    LookAnd
    0.61
    Gambas
    0.60
    +#+#
    0.59
    ⓧ
    0.58
    migrationBuilder
    0.57
     While
    0.56
    Activations Density 0.003%

    No Known Activations