© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 416
    Prev
    Next
    INDEX
    Explanations

    industrial

    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
    rrggbb
    -0.75
     يتيمه
    -0.70
    OGND
    -0.70
     تانيه
    -0.69
    Климат
    -0.68
    المناصب
    -0.68
    (!__
    -0.64
    rungsseite
    -0.63
    CodedInputStream
    -0.63
     للاسماء
    -0.63
    POSITIVE LOGITS
     transfieras
    0.50
    xmlns
    0.44
    παι
    0.42
     Internet
    0.42
     best
    0.41
     internet
    0.40
     ^{-
    0.40
     Full
    0.39
     the
    0.39
     Internal
    0.39
    Activations Density 0.097%

    No Known Activations