© 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. 1-CLT-HP
    7. 10320
    Prev
    Next
    INDEX
    Explanations

    granule

    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
     granules
    -1.77
     granule
    -1.67
     granulated
    -0.58
    Tis
    -0.55
    ism
    -0.54
    gran
    -0.50
     granular
    -0.50
     Gran
    -0.50
    omes
    -0.50
    ites
    -0.49
    POSITIVE LOGITS
     ostrich
    0.61
     VJ
    0.60
     estimés
    0.60
     Payable
    0.56
    Jeden
    0.55
     acetic
    0.55
     carbonic
    0.54
    ơm
    0.54
     Peasant
    0.54
     Drafting
    0.54
    Activations Density 0.013%

    No Known Activations