© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    geology

    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
     Diſ
    -1.45
     Efq
    -1.41
     Monfieur
    -1.40
     purpoſe
    -1.38
     myſelf
    -1.36
     reaſon
    -1.34
     ſeveral
    -1.34
     itſelf
    -1.34
     pleaſure
    -1.34
     Theſe
    -1.33
    POSITIVE LOGITS
     to
    0.67
    s
    0.66
     in
    0.66
     for
    0.64
     f
    0.64
     di
    0.59
     l
    0.57
    ,
    0.57
     n
    0.57
     k
    0.57
    Activations Density 0.517%

    No Known Activations