© 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. 4-CLT-HP
    7. 889
    Prev
    Next
    INDEX
    Explanations

    of

    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
    chossen
    -0.46
     urč
    -0.45
     upper
    -0.44
    kuuta
    -0.44
    介
    -0.44
     high
    -0.42
    ec
    -0.41
     alta
    -0.40
    ბ
    -0.40
     alto
    -0.40
    POSITIVE LOGITS
    mybatisplus
    0.89
     المعيارى
    0.84
    URLException
    0.72
     FetchType
    0.72
    AxisAlignment
    0.70
    makeConstraints
    0.70
    enumi
    0.68
    sidemargin
    0.68
    ioutil
    0.68
    ViewImports
    0.67
    Activations Density 0.008%

    No Known Activations