© 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. 92181
    Prev
    Next
    INDEX
    Explanations

    Doug

    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
     Doug
    -1.89
    Doug
    -1.55
    doug
    -0.63
    Xna
    -0.57
    tvguidetime
    -0.56
     Douglas
    -0.56
    windowFixed
    -0.51
    Kaieteur
    -0.50
    enterOuterAlt
    -0.49
     Pingback
    -0.49
    POSITIVE LOGITS
    Билгалдахарш
    0.63
     Bescheid
    0.58
    brooke
    0.55
    ndale
    0.55
    SourceChecksum
    0.55
    IVATION
    0.53
    fazione
    0.52
    lização
    0.52
    achal
    0.52
    Leaf
    0.52
    Activations Density 0.477%

    No Known Activations