© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1497
    Prev
    Next
    INDEX
    Explanations

    dilution

    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
     dilute
    -0.87
     dilution
    -0.85
     diluted
    -0.82
     dil
    -0.71
    '])->
    -0.69
     dilu
    -0.62
     Dilution
    -0.62
    dil
    -0.62
    Dilution
    -0.61
     dilutions
    -0.60
    POSITIVE LOGITS
    PreferredItem
    0.65
    SharedDtor
    0.61
     Италијани
    0.57
    AndEndTag
    0.56
    setVerticalGroup
    0.55
     विश्वसनीयता
    0.54
    SharedCtor
    0.53
    cinogenicity
    0.53
    SourceChecksum
    0.52
     communities
    0.52
    Activations Density 0.004%

    No Known Activations