© 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. 20-CLT-HP
    7. 77682
    Prev
    Next
    INDEX
    Explanations

    cost

    np_max-act-logits · 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
    TIER
    -0.53
     nakalista
    -0.52
    KommentareTeilen
    -0.50
     gezet
    -0.49
     lèvres
    -0.48
     skär
    -0.47
    kháu
    -0.47
    الإنجليزية
    -0.47
     vagues
    -0.47
     ju
    -0.46
    POSITIVE LOGITS
    Kariera
    0.62
     Alco
    0.51
     ujednoznacz
    0.50
    CppMethod
    0.50
    ciss
    0.50
    aarrggbb
    0.49
    SpringRunner
    0.49
     Passe
    0.49
    mentaux
    0.47
     handleMessage
    0.47
    Activations Density 0.003%

    No Known Activations