© 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. 45783
    Prev
    Next
    INDEX
    Explanations

    suffering

    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
    joba
    -0.45
    bena
    -0.43
    muñ
    -0.43
    }^{-}$
    -0.41
     XCTest
    -0.39
    lown
    -0.38
     $('
    -0.38
     undervis
    -0.38
    wyk
    -0.38
     raffredd
    -0.38
    POSITIVE LOGITS
    دانشنامهٔ
    0.68
    MLLoader
    0.67
    urlencoded
    0.67
    piles
    0.65
    +:+
    0.61
     nakalista
    0.60
    astéroïdes
    0.60
    __':
    0.59
    χαν
    0.59
     unblock
    0.59
    Activations Density 0.016%

    No Known Activations