© 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. 0-CLT-HP
    7. 38562
    Prev
    Next
    INDEX
    Explanations

    Subjective descriptions/opinions

    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
    LookAnd
    -0.89
    sizeCache
    -0.83
    RetentionPolicy
    -0.82
     saites
    -0.80
    +#+#
    -0.79
     cref
    -0.78
    parsedMessage
    -0.77
    invokeLater
    -0.77
    onAttach
    -0.77
    UnknownFields
    -0.76
    POSITIVE LOGITS
    ly
    0.61
     autorytatywna
    0.44
     naman
    0.44
     estimés
    0.40
    East
    0.39
    West
    0.38
    .$.
    0.38
    наче
    0.36
     morto
    0.36
     образом
    0.35
    Activations Density 1.320%

    No Known Activations