© 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. 0-CLT-HP
    7. 95142
    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
    -1.85
    features
    -1.27
    Features
    -1.13
     Features
    -1.06
     feature
    -1.02
     FEATURES
    -0.77
    feature
    -0.76
    i
    -0.74
    Feature
    -0.73
     fitur
    -0.69
    POSITIVE LOGITS
     myſelf
    1.74
     Efq
    1.73
    ſelves
    1.62
     themſelves
    1.59
     purpoſe
    1.57
     pleaſure
    1.53
     raiſ
    1.52
     uſed
    1.52
     whoſe
    1.51
    ſelf
    1.48
    Activations Density 0.255%

    No Known Activations