© 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. 44009
    Prev
    Next
    INDEX
    Explanations

    lators

    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
     al
    -0.81
     Al
    -0.69
    ologists
    -0.66
    ed
    -0.64
    ricist
    -0.63
     ant
    -0.60
     pe
    -0.59
    ellers
    -0.58
    ISTS
    -0.57
    wieś
    -0.57
    POSITIVE LOGITS
     Cæsar
    1.10
     Houſe
    1.08
     pleaſure
    1.04
     houſe
    1.00
     Anſ
    0.96
     itſelf
    0.96
     doubtnut
    0.94
     Reſ
    0.94
     greateſt
    0.94
     ſeveral
    0.93
    Activations Density 0.060%

    No Known Activations