© 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. 4-CLT-HP
    7. 4525
    Prev
    Next
    INDEX
    Explanations

    Ding

    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
    jectable
    -0.54
    ſelf
    -0.54
     ―――――
    -0.53
     Theſe
    -0.52
     Jefus
    -0.50
     Reſ
    -0.49
     ""],
    -0.48
    vera
    -0.48
     Jib
    -0.48
    auff
    -0.48
    POSITIVE LOGITS
    hy
    0.96
    hies
    0.67
     hy
    0.65
    ohy
    0.63
    hye
    0.63
    HY
    0.62
    nyk
    0.60
    ymce
    0.55
    hay
    0.55
    hkan
    0.52
    Activations Density 0.006%

    No Known Activations