© 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. 45106
    Prev
    Next
    INDEX
    Explanations

    logging and programming

    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
    sy
    -0.81
     Sy
    -0.65
    tagHelperRunner
    -0.59
    yna
    -0.58
    throw
    -0.55
     Alta
    -0.54
    gi
    -0.53
    s
    -0.52
    sach
    -0.52
    sz
    -0.50
    POSITIVE LOGITS
    AnimationsModule
    0.74
    脚注の使い方
    0.70
    تقاوى
    0.69
     onOptions
    0.68
    leiding
    0.62
    WaitGroup
    0.62
    THISDAY
    0.60
    mphony
    0.59
     كومونز
    0.59
    Према
    0.59
    Activations Density 0.165%

    No Known Activations