© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92553
    Prev
    Next
    INDEX
    Explanations

    ted

    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
     فريبيس
    -0.51
    verwijspagina
    -0.49
     مشين
    -0.46
    ########.
    -0.39
    fois
    -0.39
    cheibe
    -0.38
    manera
    -0.38
    Hauptartikel
    -0.37
    SBATCH
    -0.37
    igslist
    -0.37
    POSITIVE LOGITS
    writeFieldEnd
    0.70
    oredCriteria
    0.68
     Mares
    0.63
    (!__
    0.63
    mtrl
    0.61
    QObject
    0.60
     disambiguazione
    0.60
    Източници
    0.59
    glDelete
    0.59
    pregnant
    0.58
    Activations Density 0.004%

    No Known Activations