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. 1-CLT-HP
    4. 45110
    Prev
    Next
    INDEX
    Explanations

    level

    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
     level
    -1.72
     Level
    -1.55
    Level
    -1.52
     LEVEL
    -1.52
    level
    -1.52
    LEVEL
    -1.37
     levels
    -1.25
     nível
    -1.22
     Levels
    -1.20
     nivel
    -1.19
    POSITIVE LOGITS
    +#+#
    0.60
    ToScroll
    0.55
    omin
    0.55
    jooq
    0.53
    /\/
    0.52
    auto
    0.51
     wildcard
    0.50
    Prompt
    0.49
    ask
    0.48
     Prompt
    0.48
    Activations Density 0.130%

    No Known Activations