© 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. 94160
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    +#+#
    -0.56
    Geografie
    -0.55
     lò
    -0.54
    providedIn
    -0.53
     estekak
    -0.50
     Mela
    -0.49
    Atsauces
    -0.49
    +:+
    -0.47
    \{\\
    -0.47
    spesies
    -0.46
    POSITIVE LOGITS
    ImageContext
    0.87
     étoit
    0.75
     Monfieur
    0.73
     auroit
    0.72
    onViewCreated
    0.70
     Theſe
    0.68
    contentLoaded
    0.66
    webElementXpaths
    0.65
     itſelf
    0.65
     avoient
    0.64
    Activations Density 1.639%

    No Known Activations