© 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. 5-CLT-HP
    7. 92432
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
     can
    -0.44
     entanto
    -0.44
     I
    -0.44
     she
    -0.43
     they
    -0.43
    in
    -0.42
     says
    -0.41
     come
    -0.40
     he
    -0.40
     cannot
    -0.39
    POSITIVE LOGITS
     FetchType
    0.82
     CreateTagHelper
    0.78
    parsedMessage
    0.77
     BoxFit
    0.76
    HomeAsUpEnabled
    0.75
     '\\;'
    0.73
    TypedDataSet
    0.72
    DockStyle
    0.71
    SharedDtor
    0.70
     EdgeInsets
    0.69
    Activations Density 0.013%

    No Known Activations