© 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. 68
    Prev
    Next
    INDEX
    Explanations

    DF

    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
     الحره
    -1.02
    LookAnd
    -0.82
     للاسماء
    -0.80
     ―――――
    -0.73
     Houſe
    -0.71
     Diſ
    -0.71
     Shakspeare
    -0.71
     समीक्षाएं
    -0.70
     purpoſe
    -0.69
     Monfieur
    -0.69
    POSITIVE LOGITS
    testens
    0.44
     its
    0.44
    kości
    0.40
     satisfactorily
    0.38
     qué
    0.37
    ado
    0.37
    之所以
    0.36
    __(/*!
    0.36
    Parce
    0.36
    GOTREF
    0.35
    Activations Density 0.029%

    No Known Activations