© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97755
    Prev
    Next
    INDEX
    Explanations

    negation, denials

    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
     nor
    -0.88
     CreateTagHelper
    -0.85
    endphp
    -0.84
    QMetaType
    -0.80
    nor
    -0.77
    InvalidProtocol
    -0.77
    SBATCH
    -0.72
    oa̍t
    -0.71
    Nor
    -0.68
     للمعارف
    -0.68
    POSITIVE LOGITS
     instead
    0.44
     plutôt
    0.43
     simply
    0.43
     gewoon
    0.43
     sometimes
    0.41
     might
    0.41
     zamiast
    0.41
     manchmal
    0.40
     TAMBÉM
    0.40
     rather
    0.40
    Activations Density 0.011%

    No Known Activations