© 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. 43967
    Prev
    Next
    INDEX
    Explanations

    Latex/math expression

    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
    olute
    -1.62
     '').
    -0.61
     merit
    -0.57
    TabIndex
    -0.56
     $\
    -0.54
    wheres
    -0.50
     "").
    -0.49
    textbackslash
    -0.48
     RequestMethod
    -0.46
    galan
    -0.46
    POSITIVE LOGITS
    المناصب
    0.86
     beginnetje
    0.81
    complexContent
    0.77
    RTEE
    0.74
     resourceCulture
    0.70
     betweenstory
    0.69
    contentLoaded
    0.68
     Réponses
    0.68
    windowFixed
    0.67
    featureID
    0.66
    Activations Density 0.135%

    No Known Activations