© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43177
    Prev
    Next
    INDEX
    Explanations

    negativity

    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
    findpost
    -0.53
     ModelExpression
    -0.52
     GenerationType
    -0.50
     isInitialized
    -0.49
    Phew
    -0.48
    FTFY
    -0.47
    ytick
    -0.47
    bulletin
    -0.46
    közi
    -0.45
    Климат
    -0.45
    POSITIVE LOGITS
    ness
    1.15
    er
    1.03
    ster
    0.89
    ers
    0.86
    sters
    0.85
    est
    0.84
    theless
    0.81
    ity
    0.80
    ER
    0.75
    ties
    0.75
    Activations Density 0.468%

    No Known Activations