Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73876
    Prev
    Next
    INDEX
    Explanations

    Words starting with "e"

    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
     насељу
    -0.80
    IntoConstraints
    -0.69
    enumii
    -0.64
    AnimationsModule
    -0.64
    ConstraintMaker
    -0.63
    omock
    -0.62
    BufferException
    -0.59
     OM
    -0.59
    //
    -0.59
    hoga
    -0.59
    POSITIVE LOGITS
    ep
    0.84
    eps
    0.72
    ej
    0.65
    eb
    0.63
    eper
    0.62
    ez
    0.61
    epa
    0.59
    eg
    0.56
    ek
    0.56
    epis
    0.56
    Activations Density 0.001%

    No Known Activations