© 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. 5-CLT-HP
    7. 98192
    Prev
    Next
    INDEX
    Explanations

    weight-related topics

    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
     weights
    -0.76
     weight
    -0.71
    weight
    -0.57
    weights
    -0.57
     threads
    -0.56
     contributions
    -0.52
     Weight
    -0.52
     efforts
    -0.50
     loss
    -0.50
     weighting
    -0.48
    POSITIVE LOGITS
    Datuak
    0.80
     يتيمه
    0.73
    Diweddarwch
    0.66
    ReusableCell
    0.64
    Geplaatst
    0.63
    FunctionFlags
    0.62
     Administrativna
    0.59
     geleverd
    0.59
     चीज़ों
    0.58
    Попис
    0.58
    Activations Density 0.001%

    No Known Activations