© 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. 5-CLT-HP
    7. 91828
    Prev
    Next
    INDEX
    Explanations

    at

    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
    sieg
    -0.53
    showMessage
    -0.47
    Hrsg
    -0.46
    ENOMEM
    -0.46
    unknownFields
    -0.46
     strtotime
    -0.45
    IUrlHelper
    -0.44
    mijn
    -0.43
     Kerja
    -0.43
     Interpretation
    -0.43
    POSITIVE LOGITS
    ">//
    0.67
    
    0.63
    intios
    0.62
     المعيارى
    0.61
     habet
    0.56
     propOrder
    0.56
    OGND
    0.56
    ніципа
    0.54
    LayoutStyle
    0.53
    })->
    0.53
    Activations Density 0.030%

    No Known Activations