© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12177
    Prev
    Next
    INDEX
    Explanations

    values and beliefs

    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
     CONTROLS
    -0.54
    retur
    -0.54
    codable
    -0.54
    Controls
    -0.50
    ANNELS
    -0.48
     Quarto
    -0.47
    tivamente
    -0.46
    undes
    -0.46
     Schalt
    -0.46
    økt
    -0.46
    POSITIVE LOGITS
    findpost
    0.83
    AnimationsModule
    0.75
     تضيفلها
    0.68
    хьтан
    0.68
    SharedDtor
    0.65
    MLLoader
    0.64
    Personendaten
    0.63
     about
    0.60
    WriteTagHelper
    0.59
    smithy
    0.59
    Activations Density 0.002%

    No Known Activations