© 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. 96803
    Prev
    Next
    INDEX
    Explanations

    glass

    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
    es
    -0.48
    Jeografia
    -0.47
    eam
    -0.47
    ese
    -0.46
    pexpr
    -0.45
    l
    -0.44
    em
    -0.42
     ouvriers
    -0.42
     particuliers
    -0.42
     Diff
    -0.42
    POSITIVE LOGITS
    onViewCreated
    0.73
    }))
    0.72
     Houſe
    0.67
    Bibliograf
    0.65
    ViewStyle
    0.65
    djangoproject
    0.64
     houſe
    0.64
    spur
    0.64
     Waray
    0.64
     itſelf
    0.63
    Activations Density 0.002%

    No Known Activations