© 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. 43305
    Prev
    Next
    INDEX
    Explanations

    hamsters

    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
     Paglinawan
    -0.82
     beginnetje
    -0.76
    LookAnd
    -0.73
    NameInMap
    -0.70
    IsContent
    -0.69
    Хьажоргаш
    -0.69
     propOrder
    -0.68
     ComVisible
    -0.67
    تقاوى
    -0.66
     Signalez
    -0.65
    POSITIVE LOGITS
    ing
    0.65
    ed
    0.53
    ING
    0.52
    DotNetBar
    0.50
     emot
    0.49
    sedi
    0.48
    cast
    0.48
    peted
    0.48
     Peker
    0.48
    ينج
    0.47
    Activations Density 0.178%

    No Known Activations