© 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. 1-CLT-HP
    7. 13649
    Prev
    Next
    INDEX
    Explanations

    features

    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
     features
    -1.41
     feature
    -1.35
     Features
    -1.27
     Feature
    -1.19
    features
    -1.18
    feature
    -1.15
    Features
    -1.13
     FEATURES
    -1.07
    Feature
    -1.05
     FEATURE
    -0.97
    POSITIVE LOGITS
     of
    0.62
     imprimée
    0.57
     réglable
    0.55
     pioggia
    0.53
     vectorielle
    0.52
     africaine
    0.52
     nationaux
    0.51
    SPD
    0.51
     alimentaire
    0.49
    spender
    0.49
    Activations Density 0.064%

    No Known Activations