© 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. 5-CLT-HP
    7. 2219
    Prev
    Next
    INDEX
    Explanations

    to

    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
     resourceCulture
    -1.00
    TestTools
    -0.87
     HasFactory
    -0.85
    RuleContext
    -0.81
    IntoConstraints
    -0.81
     فريبيس
    -0.79
    principalTable
    -0.79
     tartalomajánló
    -0.78
    ագրություններ
    -0.77
     समीक्षक
    -0.77
    POSITIVE LOGITS
     die
    0.53
     Die
    0.47
     own
    0.43
     file
    0.43
     say
    0.40
     report
    0.40
     land
    0.39
     forgive
    0.38
     later
    0.38
     name
    0.37
    Activations Density 0.001%

    No Known Activations