© 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. 5-CLT-HP
    7. 92640
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
     reciprocal
    -0.57
     gelungen
    -0.52
     confidence
    -0.50
    iconCls
    -0.48
    AnimationsModule
    -0.48
    contentInset
    -0.47
     trusted
    -0.45
     harmonious
    -0.45
    idemia
    -0.44
    кор
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.83
     resourceCulture
    0.71
     forgetting
    0.68
     limiti
    0.66
     limits
    0.66
     underestimate
    0.65
     forgets
    0.64
     only
    0.63
     limit
    0.63
    forget
    0.63
    Activations Density 0.052%

    No Known Activations