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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73957
    Prev
    Next
    INDEX
    Explanations

    groups

    np_max-act-logits · 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
    ValueStyle
    -0.61
     [*]
    -0.51
    adecimal
    -0.50
    COUVER
    -0.49
    ghed
    -0.48
    enumi
    -0.46
    لع
    -0.46
     Belast
    -0.46
    Clik
    -0.45
    atile
    -0.43
    POSITIVE LOGITS
    evos
    0.64
    олові
    0.62
     advisor
    0.58
    intios
    0.57
     للاسماء
    0.57
    ConstraintMaker
    0.57
    UnusedPrivate
    0.56
     adviser
    0.56
    Personensuche
    0.56
     Juana
    0.56
    Activations Density 0.001%

    No Known Activations