© 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. 1-CLT-HP
    7. 11987
    Prev
    Next
    INDEX
    Explanations

    igh

    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
    igh
    -1.53
    IGHT
    -1.37
    ight
    -1.34
    IGH
    -1.13
    ights
    -1.11
    IGHTS
    -0.89
    ighty
    -0.83
    light
    -0.79
    ighth
    -0.79
    ighted
    -0.69
    POSITIVE LOGITS
    ConstraintMaker
    0.62
    QMetaType
    0.59
    AxisAlignment
    0.57
     ModelExpression
    0.57
    MethodManager
    0.55
    исленность
    0.54
    CreateMap
    0.52
    ngdoc
    0.52
    HttpPut
    0.51
     OnInit
    0.50
    Activations Density 0.160%

    No Known Activations