© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96755
    Prev
    Next
    INDEX
    Explanations

    below

    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
     anymore
    -0.98
     nor
    -0.88
     any
    -0.74
     melainkan
    -0.72
    ύτε
    -0.72
     anything
    -0.70
     necessarily
    -0.67
    帖最后由
    -0.65
     or
    -0.64
     mitään
    -0.64
    POSITIVE LOGITS
    })();
    0.50
    RegistryLite
    0.50
    CodedInputStream
    0.48
    somewhere
    0.48
    RetentionPolicy
    0.48
    Kaieteur
    0.46
     various
    0.46
    UrlResolution
    0.45
    "]));
    0.45
     parfois
    0.45
    Activations Density 0.008%

    No Known Activations