© 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. 4-CLT-HP
    7. 413
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     oxidation
    -0.58
     declaratory
    -0.57
    tispiece
    -0.55
     cauſe
    -0.55
    extrémité
    -0.54
     ſeveral
    -0.54
     againſt
    -0.53
     Falta
    -0.53
     AttributeSet
    -0.53
    ]?.
    -0.53
    POSITIVE LOGITS
    licenses
    0.55
     TextAlign
    0.54
    shadowRadius
    0.52
     كومونز
    0.51
     ro
    0.51
    modelBuilder
    0.48
    Архівовано
    0.48
    ModelSerializer
    0.47
    native
    0.46
    porus
    0.45
    Activations Density 0.005%

    No Known Activations