© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45163
    Prev
    Next
    INDEX
    Explanations

    receiver

    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
     CreateTagHelper
    -0.90
     propOrder
    -0.80
    ConstraintMaker
    -0.77
    migrationBuilder
    -0.74
    VIAF
    -0.71
    MigrationBuilder
    -0.70
     MainAxisSize
    -0.69
    matchCondition
    -0.69
     VIDEOTAPE
    -0.69
     Baillargeon
    -0.69
    POSITIVE LOGITS
    <bos>
    0.56
     logic
    0.51
     actuators
    0.48
     I
    0.46
     interpreters
    0.46
    ’
    0.46
     engine
    0.45
     track
    0.45
     loop
    0.45
     loops
    0.44
    Activations Density 0.148%

    No Known Activations