© 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. 5847
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    tagHelperRunner
    -0.84
     disambiguazione
    -0.78
    hyrchwyd
    -0.76
    IsContent
    -0.66
    RenderAtEndOf
    -0.65
    verwijspagina
    -0.65
     Dalio
    -0.61
     autorytatywna
    -0.61
    Hentet
    -0.60
     nahilalakip
    -0.60
    POSITIVE LOGITS
     LUMP
    0.51
     manqué
    0.45
    rats
    0.44
     rats
    0.44
    mice
    0.43
     companyId
    0.42
    GoogleApiClient
    0.41
    ereo
    0.41
    ρί
    0.41
     beaten
    0.40
    Activations Density 0.053%

    No Known Activations