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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94497
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    ing
    -1.79
    ING
    -1.24
    ed
    -0.61
    ング
    -0.61
    ings
    -0.57
    ↵↵
    -0.57
    ный
    -0.57
    inge
    -0.56
    ingin
    -0.56
    ingh
    -0.54
    POSITIVE LOGITS
    ̍t
    0.84
    NameInMap
    0.84
    TagMode
    0.81
     يتيمه
    0.80
    rawDesc
    0.78
    Viited
    0.76
    AndEndTag
    0.75
    @[+][
    0.73
    writeFieldEnd
    0.73
    MigrationBuilder
    0.72
    Activations Density 0.450%

    No Known Activations