© 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. 5-CLT-HP
    7. 97594
    Prev
    Next
    INDEX
    Explanations

    -

    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
    adaptiveStyles
    -0.61
     Fonds
    -0.55
     Finish
    -0.55
    MessageOf
    -0.54
    APIS
    -0.53
     Dass
    -0.52
     finish
    -0.52
     finis
    -0.52
     fund
    -0.51
    agisse
    -0.51
    POSITIVE LOGITS
    PMailer
    0.53
    @[+][
    0.53
    principalColumn
    0.51
    rungsseite
    0.50
    ungkinan
    0.47
    GeneratedCode
    0.47
     /*#__
    0.46
    1
    0.45
     للمعارف
    0.44
    withIdentifier
    0.44
    Activations Density 0.024%

    No Known Activations