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. 44515
    Prev
    Next
    INDEX
    Explanations

    of

    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
    mas
    -0.59
     of
    -0.56
    ly
    -0.50
    g
    -0.49
    pk
    -0.47
    on
    -0.46
    ↵
    -0.46
    zo
    -0.46
     and
    -0.45
    3
    -0.45
    POSITIVE LOGITS
    AndEndTag
    1.13
    MigrationBuilder
    1.09
     للاسماء
    1.03
    LookAnd
    0.98
     '\\;'
    0.96
    etheless
    0.94
    .*")]
    0.90
    InjectAttribute
    0.89
     تانيه
    0.88
    StoryboardSegue
    0.88
    Activations Density 0.118%

    No Known Activations