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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45013
    Prev
    Next
    INDEX
    Explanations

    Essential

    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
    efully
    -0.65
     permutations
    -0.63
    ly
    -0.59
    eful
    -0.49
    ying
    -0.49
    worth
    -0.49
    PreExecute
    -0.49
    IgnoreCase
    -0.48
     Essential
    -0.48
    WORTH
    -0.47
    POSITIVE LOGITS
    UserScript
    0.97
    Tikang
    0.79
    TagMode
    0.77
    Personensuche
    0.72
    pidou
    0.71
    EndContext
    0.69
     насељу
    0.68
    UnknownFieldSet
    0.66
     gynhyrchwyd
    0.65
    مصادر
    0.62
    Activations Density 0.114%

    No Known Activations