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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97986
    Prev
    Next
    INDEX
    Explanations

    Compton

    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
    ME
    -0.69
    oh
    -0.69
    dar
    -0.54
    ohs
    -0.51
    发表于
    -0.48
     Compton
    -0.44
     cur
    -0.44
     me
    -0.42
    eld
    -0.42
     sou
    -0.42
    POSITIVE LOGITS
     myſelf
    1.03
     itſelf
    0.93
     himſelf
    0.87
     ſtate
    0.86
     themſelves
    0.84
     purpoſe
    0.84
     ſeveral
    0.84
     poffe
    0.83
    ScopeManager
    0.82
    UrlResolution
    0.82
    Activations Density 0.758%

    No Known Activations