© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10742
    Prev
    Next
    INDEX
    Explanations

    meeting

    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
    homonymie
    -0.70
     BoxFit
    -0.67
    fromCharCode
    -0.66
     createSprite
    -0.65
    (!__
    -0.64
     reaſon
    -0.58
    Personendaten
    -0.57
    optarg
    -0.57
     '\\;'
    -0.57
    Portail
    -0.56
    POSITIVE LOGITS
    libft
    0.47
     mast
    0.42
    Locator
    0.41
    доступ
    0.41
     aberta
    0.40
    //
    0.40
     co
    0.40
     خل
    0.40
     terbuka
    0.40
    rovnik
    0.40
    Activations Density 0.012%

    No Known Activations