© 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. 1-CLT-HP
    7. 15580
    Prev
    Next
    INDEX
    Explanations

    oggle

    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
    oggle
    -1.27
    Дереккөздер
    -0.71
     ***!
    -0.71
     فريبيس
    -0.70
     ujednoznacz
    -0.64
    modb
    -0.62
    expandindo
    -0.62
    toBeDefined
    -0.61
    StructEnd
    -0.60
    íš
    -0.60
    POSITIVE LOGITS
     tradicionais
    0.46
     चाहते
    0.42
     CreateTagHelper
    0.42
    attack
    0.41
     LIGHTS
    0.41
     préférable
    0.39
    ylen
    0.39
     lights
    0.39
    сре
    0.39
    nonatomic
    0.38
    Activations Density 0.005%

    No Known Activations