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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2318
    Prev
    Next
    INDEX
    Explanations

    animation

    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
    tagHelperRunner
    -0.68
    __':
    -0.49
     ""],
    -0.48
    ритори
    -0.47
    новништво
    -0.47
    RTEX
    -0.46
    migrationBuilder
    -0.45
    SerializeField
    -0.45
    jedis
    -0.44
     Offisielt
    -0.44
    POSITIVE LOGITS
     delays
    0.59
     Blooming
    0.58
    balleur
    0.56
     delay
    0.55
    TagHelper
    0.54
    itesse
    0.54
     Delays
    0.54
     dure
    0.52
     Events
    0.52
    speed
    0.52
    Activations Density 0.007%

    No Known Activations