© 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. 20-CLT-HP
    7. 76886
    Prev
    Next
    INDEX
    Explanations

    technical/scientific/programming contexts

    np_max-act-logits · 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
    classnames
    -0.51
    orsese
    -0.50
     colic
    -0.46
    ReadLine
    -0.44
     Comer
    -0.44
     deten
    -0.43
    ByDefault
    -0.43
    ourne
    -0.42
    ณ์
    -0.42
     Dated
    -0.41
    POSITIVE LOGITS
    Espèce
    0.64
     iArr
    0.59
    figcaption
    0.57
    NewUrlParser
    0.57
    Supplies
    0.56
    Assistance
    0.56
     immediate
    0.55
    providedIn
    0.55
     snippetHide
    0.54
    HttpFoundation
    0.54
    Activations Density 0.000%

    No Known Activations