© 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. 11892
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
    pti
    -1.09
    pta
    -0.93
     Dunlap
    -0.46
     pitted
    -0.46
    createComponent
    -0.45
     spørgsmål
    -0.45
     CAP
    -0.44
    InteropServices
    -0.43
    anco
    -0.43
    共和国
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.72
    DockStyle
    0.67
     Normdatei
    0.65
     <=",
    0.64
    ynchronously
    0.63
    NewGuid
    0.63
    ConstraintMaker
    0.62
     مرئيه
    0.61
    ">—
    0.61
    BindView
    0.60
    Activations Density 0.028%

    No Known Activations