© 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. 4-CLT-HP
    7. 4509
    Prev
    Next
    INDEX
    Explanations

    as

    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
    PerformLayout
    -0.77
    DeleteBehavior
    -0.75
    findpost
    -0.75
    Personendaten
    -0.71
    ########.
    -0.68
     дописавши
    -0.68
    ConstraintMaker
    -0.64
    WebServlet
    -0.64
     '\\;'
    -0.63
     bezeichneter
    -0.63
    POSITIVE LOGITS
    esgue
    0.50
     eines
    0.44
     a
    0.43
    λοι
    0.41
    żeli
    0.41
    Antoine
    0.41
    NCT
    0.40
     cabe
    0.39
     our
    0.39
    OfMonth
    0.38
    Activations Density 0.003%

    No Known Activations