© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76079
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    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
     ujednoznacz
    -0.66
     Extragalactic
    -0.54
    scriptcase
    -0.52
    rungsseite
    -0.51
    庁
    -0.48
    WebpackPlugin
    -0.47
    ]")]
    -0.46
    SharedCtor
    -0.45
    lemish
    -0.44
    racene
    -0.44
    POSITIVE LOGITS
    0
    0.87
    𝟶
    0.55
    دانشنامهٔ
    0.55
    orama
    0.52
    ⁄
    0.52
    تقاوى
    0.50
    XmlSchema
    0.50
    tagext
    0.50
     Signalez
    0.49
    ActionCreators
    0.49
    Activations Density 0.000%

    No Known Activations