© 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. 71714
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific strings

    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
    ValueGeneration
    -0.66
    setVerticalGroup
    -0.66
    neté
    -0.56
    AnchorStyles
    -0.56
    }{*}{}
    -0.54
    PerformLayout
    -0.54
    anterie
    -0.54
    verwijspagina
    -0.53
     AspNetCore
    -0.53
    stini
    -0.53
    POSITIVE LOGITS
    TagMode
    0.60
    SceneManagement
    0.56
    ButterKnife
    0.56
     فريبيس
    0.53
     deport
    0.52
    bufio
    0.51
    ma
    0.48
    SequentialGroup
    0.48
     deported
    0.48
    MA
    0.48
    Activations Density 0.000%

    No Known Activations