© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    nature and 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
    出版年
    -0.75
     myſelf
    -0.65
     themſelves
    -0.65
     purpoſe
    -0.64
     ſtate
    -0.63
     himſelf
    -0.63
     faſt
    -0.60
     ſmall
    -0.58
     naught
    -0.57
     ſever
    -0.57
    POSITIVE LOGITS
     مشين
    0.58
     composition
    0.50
    avaient
    0.49
    getSupport
    0.47
     παν
    0.46
     כלל
    0.42
    jetbrains
    0.42
    inerja
    0.42
    Sud
    0.41
    weli
    0.41
    Activations Density 0.001%

    No Known Activations