© 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. 4-CLT-HP
    7. 4340
    Prev
    Next
    INDEX
    Explanations

    s

    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
     CURIAM
    -0.57
     varandra
    -0.53
     kasarigan
    -0.52
    GEBURTSDATUM
    -0.52
    AndEndTag
    -0.48
    SourceChecksum
    -0.47
     مشين
    -0.47
     variés
    -0.46
     manquer
    -0.45
     wahre
    -0.45
    POSITIVE LOGITS
     use
    0.74
     claim
    0.69
     efforts
    0.67
     attempt
    0.62
     studies
    0.62
     investigations
    0.61
     study
    0.59
     attempts
    0.59
     maxim
    0.58
     notion
    0.58
    Activations Density 0.000%

    No Known Activations