© 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. 0-CLT-HP
    7. 95265
    Prev
    Next
    INDEX
    Explanations

    mammals

    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
    -0.78
     Paglinawan
    -0.76
    birds
    -0.71
    verwijspagina
    -0.70
    IsMutable
    -0.69
    Personendaten
    -0.66
    webElementXpaths
    -0.66
    Chham
    -0.66
     Roskov
    -0.65
    payers
    -0.65
    POSITIVE LOGITS
     are
    0.71
     that
    0.63
     have
    0.63
     were
    0.59
    .
    0.55
    chutz
    0.54
     such
    0.54
     infected
    0.54
    ,
    0.53
    Autowired
    0.52
    Activations Density 0.250%

    No Known Activations