© 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. 0-CLT-HP
    7. 92934
    Prev
    Next
    INDEX
    Explanations

    repository

    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
    Repository
    -0.96
    AxisAlignment
    -0.80
    ⓧ
    -0.79
    angered
    -0.77
    MLLoader
    -0.74
    amous
    -0.71
    MessageTagHelper
    -0.65
    getRepository
    -0.65
    repository
    -0.63
    setVerticalGroup
    -0.62
    POSITIVE LOGITS
     lenker
    0.51
     estekak
    0.51
    enumi
    0.46
     Anfitrión
    0.43
     pesce
    0.42
     Turismo
    0.41
     Rossini
    0.41
    connected
    0.40
     Esperanto
    0.40
     linker
    0.40
    Activations Density 1.483%

    No Known Activations