© 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. 92968
    Prev
    Next
    INDEX
    Explanations

    Readiness

    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
     ready
    -0.65
    ToScroll
    -0.56
     available
    -0.52
    Hentet
    -0.49
    ready
    -0.49
    onimo
    -0.48
    IBUS
    -0.45
     READY
    -0.43
     sẵn
    -0.43
    istry
    -0.42
    POSITIVE LOGITS
     externi
    0.72
    bootstrapcdn
    0.71
    ագրություններ
    0.69
     estekak
    0.66
    BeginInit
    0.66
     Efq
    0.65
    ValueGeneration
    0.64
    transQ
    0.63
    afficheront
    0.62
    MigrationBuilder
    0.61
    Activations Density 0.006%

    No Known Activations