© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 908
    Prev
    Next
    INDEX
    Explanations

    names

    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
    transQ
    -0.81
    ."],
    -0.78
    ."]
    -0.73
    parsedMessage
    -0.73
     AssemblyVersion
    -0.72
     uintptr
    -0.72
    .”—
    -0.71
    msgTypes
    -0.70
    .—
    -0.68
    SequentialGroup
    -0.68
    POSITIVE LOGITS
    קישורים
    0.51
     Drapeau
    0.40
    itinéraire
    0.39
    šanai
    0.36
    UNICIP
    0.34
     cérami
    0.34
    цездатний
    0.33
    andte
    0.33
     dieux
    0.33
     automatiques
    0.32
    Activations Density 0.012%

    No Known Activations