Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 779
    Prev
    Next
    INDEX
    Explanations

    Prop

    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
    s
    -0.96
    IndentedString
    -0.75
    MigrationBuilder
    -0.73
    sab
    -0.71
    ی
    -0.68
    sau
    -0.66
     ExecuteAsync
    -0.66
    bootstrapcdn
    -0.66
    StoryboardSegue
    -0.65
    sana
    -0.65
    POSITIVE LOGITS
    bo
    0.57
    ance
    0.56
    self
    0.56
    aro
    0.55
    ResumeLayout
    0.55
    pe
    0.52
    up
    0.52
     مشين
    0.51
    ano
    0.50
    ia
    0.49
    Activations Density 0.092%

    No Known Activations