© 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. 91075
    Prev
    Next
    INDEX
    Explanations

    chemo

    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
     pleaſure
    -1.17
     myſelf
    -1.07
     themſelves
    -1.05
     itſelf
    -1.04
     poffe
    -1.01
     purpoſe
    -1.01
     himſelf
    -1.00
    ſelves
    -0.98
     Jefus
    -0.98
    ſelf
    -0.97
    POSITIVE LOGITS
    t
    0.72
    e
    0.69
    ,
    0.66
    a
    0.62
    ss
    0.60
     of
    0.59
    y
    0.58
    eli
    0.57
    т
    0.57
    i
    0.57
    Activations Density 0.078%

    No Known Activations