© 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. 73021
    Prev
    Next
    INDEX
    Explanations

    Curt

    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
    styleType
    -0.55
    IntoConstraints
    -0.51
    kloped
    -0.49
     ExecuteAsync
    -0.49
    stonia
    -0.46
    Chees
    -0.45
    osoba
    -0.44
    Nasc
    -0.44
     AssemblyTitle
    -0.43
     Chees
    -0.43
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.66
    didSet
    0.62
    WebElementEntity
    0.56
    CodedInputStream
    0.56
    ///</
    0.54
    Geplaatst
    0.54
    auta
    0.52
    itude
    0.52
    rethe
    0.51
    árl
    0.51
    Activations Density 0.001%

    No Known Activations