© 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. 95009
    Prev
    Next
    INDEX
    Explanations

    wildlife

    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
    wildlife
    -1.37
     wildlife
    -1.34
     Wildlife
    -1.28
     WILDLIFE
    -1.27
    Wildlife
    -1.26
     disambiguazione
    -1.06
    extAlignment
    -1.01
     wikipagina
    -0.90
     étoient
    -0.87
     feroit
    -0.85
    POSITIVE LOGITS
    y
    0.60
    .
    0.55
    ie
    0.54
    ies
    0.52
    ing
    0.51
    ,
    0.50
    ied
    0.49
    ia
    0.49
    i
    0.48
    ’
    0.48
    Activations Density 0.192%

    No Known Activations