© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4348
    Prev
    Next
    INDEX
    Explanations

    already have

    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
     usah
    -0.47
    else
    -0.47
     verrez
    -0.42
    beat
    -0.42
    code
    -0.42
    知的
    -0.40
    iras
    -0.40
    Ndr
    -0.40
    have
    -0.39
    cshtml
    -0.39
    POSITIVE LOGITS
    StoryboardSegue
    0.88
     initComponents
    0.84
    findpost
    0.77
    цездатний
    0.75
    RegistryLite
    0.74
    sizeCache
    0.74
    addCriterion
    0.71
    الحياه
    0.69
    RenderAtEndOf
    0.69
     autorytatywna
    0.68
    Activations Density 0.008%

    No Known Activations