© 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. 45261
    Prev
    Next
    INDEX
    Explanations

    parts

    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
     myſelf
    -1.00
     itſelf
    -0.94
    ſelf
    -0.93
     pleaſure
    -0.92
     himſelf
    -0.90
    ſelves
    -0.88
     purpoſe
    -0.88
     Chriftian
    -0.85
     juſ
    -0.84
     Efq
    -0.84
    POSITIVE LOGITS
    farwyddwr
    0.50
    Itoa
    0.49
    e
    0.45
    (['/
    0.40
    Wallis
    0.40
     ferons
    0.40
    od
    0.39
    log
    0.38
    ob
    0.38
     Country
    0.38
    Activations Density 0.244%

    No Known Activations