© 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. 1-CLT-HP
    7. 15239
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    SPATH
    -0.51
    ismet
    -0.50
     editText
    -0.48
     fresa
    -0.46
    deauna
    -0.45
    edicated
    -0.45
     estimés
    -0.45
    riwal
    -0.44
     BorderRadius
    -0.44
    ggere
    -0.43
    POSITIVE LOGITS
    findpost
    0.59
    AllowUser
    0.56
    race
    0.55
     FetchType
    0.53
     Inquiry
    0.52
     inquiry
    0.51
     ModelExpression
    0.50
    IonicModule
    0.50
     Enquiry
    0.49
    qtype
    0.48
    Activations Density 0.012%

    No Known Activations