© 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. 97802
    Prev
    Next
    INDEX
    Explanations

    institutions and documentation

    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
    PO
    -0.47
    DllImport
    -0.44
    au
    -0.43
     impo
    -0.43
    Quality
    -0.42
    Xiv
    -0.41
     po
    -0.41
     kval
    -0.41
    tua
    -0.41
     HUMAN
    -0.40
    POSITIVE LOGITS
     تكبرها
    0.71
     Италијани
    0.71
    AsUp
    0.69
    rungsseite
    0.69
    istice
    0.68
     Hemingway
    0.65
    StoryboardSegue
    0.65
     Efq
    0.62
    (;;)
    0.62
    rrggbb
    0.62
    Activations Density 0.000%

    No Known Activations