© 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. 554
    Prev
    Next
    INDEX
    Explanations

    inequality

    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
     Tomar
    -0.62
     Ráp
    -0.60
    DataRow
    -0.57
     Predic
    -0.55
    ellido
    -0.55
    älv
    -0.54
    imai
    -0.53
    HOE
    -0.53
    LLO
    -0.53
    DBNull
    -0.53
    POSITIVE LOGITS
    @[+][
    0.65
    OGND
    0.57
    makeText
    0.56
    PullParser
    0.54
    ContentAsync
    0.53
     Normdatei
    0.52
    featureID
    0.52
    enterOuterAlt
    0.52
    elemField
    0.51
     EconPapers
    0.51
    Activations Density 0.251%

    No Known Activations