© 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. 91318
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency/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
    ंदीखरीदारी
    -0.59
     odkazy
    -0.54
    rungsseite
    -0.53
    Bibliograf
    -0.53
     Infórmanos
    -0.51
     lenker
    -0.50
     henvisninger
    -0.50
    neté
    -0.50
    AutoresizingMask
    -0.48
     mà
    -0.47
    POSITIVE LOGITS
     being
    1.23
     representing
    1.20
     having
    1.20
     appearing
    1.20
     taking
    1.16
     coming
    1.16
     providing
    1.14
     forming
    1.14
     serving
    1.11
     constituting
    1.10
    Activations Density 0.002%

    No Known Activations