© 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. 0-CLT-HP
    7. 92044
    Prev
    Next
    INDEX
    Explanations

    versatile

    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
     Versatile
    -0.61
    }{*}{}
    -0.61
     variables
    -0.60
    atility
    -0.60
     versatility
    -0.57
     %
    -0.57
    ChildScrollView
    -0.57
    IsMutable
    -0.55
     Relativity
    -0.55
     versatile
    -0.53
    POSITIVE LOGITS
    findpost
    0.69
     poffible
    0.68
     photolibrary
    0.65
    uxxxx
    0.65
     purpoſe
    0.63
     ſeveral
    0.62
     Majefty
    0.62
     myſelf
    0.62
     themſelves
    0.61
     torus
    0.60
    Activations Density 0.347%

    No Known Activations