© 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. 94875
    Prev
    Next
    INDEX
    Explanations

    Informal writing snippets

    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
    例句
    -0.60
     <<<<<<<<<<<<<<
    -0.54
    ISODE
    -0.51
    Comté
    -0.51
     CYTHON
    -0.51
     ubic
    -0.50
    SerializedSize
    -0.50
    #
    -0.50
    /*
    -0.48
    IntoConstraints
    -0.47
    POSITIVE LOGITS
    それとも
    0.57
     men
    0.55
    ArgsConstructor
    0.52
    parsedMessage
    0.52
    OptionsMenu
    0.51
    setArguments
    0.51
    xymatrix
    0.50
    doGet
    0.49
    zieli
    0.49
    arrows
    0.48
    Activations Density 0.023%

    No Known Activations