© 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. 12127
    Prev
    Next
    INDEX
    Explanations

    standard

    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
     ModelRenderer
    -0.79
     EconPapers
    -0.79
     gynhyrchwyd
    -0.77
     متعلقه
    -0.75
    RefNanny
    -0.75
    featureID
    -0.74
     kaarangay
    -0.71
     indisponible
    -0.69
    OGND
    -0.69
     purpoſe
    -0.67
    POSITIVE LOGITS
     aDecoder
    0.50
    NOPQRST
    0.49
     deviations
    0.47
     deviation
    0.47
    oreille
    0.44
    lardır
    0.44
    Leaks
    0.43
    rater
    0.43
    vore
    0.43
     DEC
    0.42
    Activations Density 0.012%

    No Known Activations