© 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. 45320
    Prev
    Next
    INDEX
    Explanations

    plexus

    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
    lysis
    -0.60
    ActionCreators
    -0.59
    álat
    -0.58
     pase
    -0.56
    omics
    -0.55
    LayoutStyle
    -0.54
    ning
    -0.54
    lichung
    -0.54
    auta
    -0.52
    ilation
    -0.51
    POSITIVE LOGITS
     itſelf
    0.69
    uxxxx
    0.66
     ſeveral
    0.66
     Suivez
    0.66
    ValueStyle
    0.65
     Monfieur
    0.63
     CHAPITRE
    0.60
     Anſ
    0.59
     greateſt
    0.56
     myſelf
    0.56
    Activations Density 0.207%

    No Known Activations