© 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. 1-CLT-HP
    7. 539
    Prev
    Next
    INDEX
    Explanations

    alternative

    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
     goutte
    -0.56
    malink
    -0.48
     vectorielles
    -0.48
     normaux
    -0.46
    fjspx
    -0.44
     FontFamily
    -0.44
     numériques
    -0.43
    ktır
    -0.43
     <>",
    -0.43
     uint
    -0.42
    POSITIVE LOGITS
    PerformLayout
    0.66
     hierogly
    0.65
    OGND
    0.60
     Protestantism
    0.60
     freehold
    0.60
     campsite
    0.59
     Stonehenge
    0.58
    EndInit
    0.57
     enlightenment
    0.57
     hermit
    0.57
    Activations Density 0.005%

    No Known Activations