© 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. 1-CLT-HP
    7. 45679
    Prev
    Next
    INDEX
    Explanations

    recorded

    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
    enumi
    -0.55
    saraba
    -0.51
     Stu
    -0.49
    ग्री
    -0.48
     rowspan
    -0.45
     rang
    -0.45
    Ghi
    -0.44
     parch
    -0.44
    Stu
    -0.44
    liwości
    -0.43
    POSITIVE LOGITS
    onOptions
    0.74
     transfieras
    0.69
    Autoritní
    0.67
     himo
    0.67
     doubtnut
    0.62
    drawSprites
    0.60
     estimés
    0.60
    ]]=
    0.60
     تضيفلها
    0.59
    Rujuakan
    0.58
    Activations Density 0.254%

    No Known Activations