© 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. 5-CLT-HP
    7. 96193
    Prev
    Next
    INDEX
    Explanations

    kk

    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
    -0.70
     argc
    -0.58
    geries
    -0.54
    +:+
    -0.54
    LoggerFactory
    -0.53
    LogFactory
    -0.53
    msgTypes
    -0.53
    XmlType
    -0.52
     LoggerFactory
    -0.52
    ineno
    -0.50
    POSITIVE LOGITS
    hun
    0.64
    hus
    0.62
    hu
    0.59
    HUN
    0.58
    homonymie
    0.52
    uxxxx
    0.50
    unis
    0.49
    huk
    0.48
    erequisite
    0.48
    Conven
    0.47
    Activations Density 0.001%

    No Known Activations