© 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. 76581
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
     distanciation
    -0.48
    toBe
    -0.48
    Played
    -0.47
    SerializeField
    -0.46
    ASI
    -0.45
     plays
    -0.45
     Played
    -0.45
    tiq
    -0.44
     écrit
    -0.44
    Play
    -0.43
    POSITIVE LOGITS
    хьтан
    0.76
     بيها
    0.68
     المعيارى
    0.68
     bezeichneter
    0.67
    évaluateur
    0.66
     Roskov
    0.65
    Хьажоргаш
    0.64
    Демографія
    0.60
     kaarangay
    0.59
     NSCoder
    0.58
    Activations Density 0.002%

    No Known Activations