© 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. 96433
    Prev
    Next
    INDEX
    Explanations

    Legal citations

    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
     disambiguazione
    -0.82
     Efq
    -0.63
    randomUUID
    -0.63
    omock
    -0.62
    NUMX
    -0.62
     **/
    -0.60
     juſt
    -0.59
     surla
    -0.57
    ModelAdmin
    -0.56
    mergeFrom
    -0.54
    POSITIVE LOGITS
    .
    0.50
     kasarigan
    0.49
    gehend
    0.47
    hoenix
    0.46
    CPtr
    0.45
     D
    0.44
    ↘
    0.44
    :
    0.44
     r
    0.43
     -
    0.43
    Activations Density 0.027%

    No Known Activations