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. 74424
    Prev
    Next
    INDEX
    Explanations

    names

    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
    DockStyle
    -0.59
    XMLSchema
    -0.59
    addCriterion
    -0.54
    createCanvas
    -0.54
    Portale
    -0.54
    IntoConstraints
    -0.53
    GenerationType
    -0.53
    InputBorder
    -0.53
    Geplaatst
    -0.52
    MLLoader
    -0.51
    POSITIVE LOGITS
    hosa
    0.56
     Coss
    0.53
    CrossRef
    0.52
     HttpNotFound
    0.51
    uerst
    0.50
    Geometry
    0.49
    anguardia
    0.48
     Diar
    0.48
    tych
    0.47
    uttosto
    0.47
    Activations Density 0.001%

    No Known Activations