© 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. 5-CLT-HP
    7. 95100
    Prev
    Next
    INDEX
    Explanations

    associated

    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
    vieja
    -0.50
     instanceof
    -0.50
    Diweddarwch
    -0.49
    jured
    -0.47
    extAlignment
    -0.46
     settling
    -0.46
    unches
    -0.46
    >//
    -0.45
     geboren
    -0.44
    tifkan
    -0.44
    POSITIVE LOGITS
    AutoresizingMask
    0.61
    findpost
    0.59
     OMITBAD
    0.58
     Emotion
    0.57
    ussis
    0.56
     betweenstory
    0.54
    wikidata
    0.54
     with
    0.54
    Emotion
    0.52
     bucal
    0.51
    Activations Density 0.004%

    No Known Activations