© 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. 4351
    Prev
    Next
    INDEX
    Explanations

    had

    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
    untut
    -0.46
    证明
    -0.46
    anter
    -0.43
     reports
    -0.43
    integrating
    -0.42
    precedented
    -0.41
    rigos
    -0.41
    such
    -0.41
     G
    -0.41
    reports
    -0.41
    POSITIVE LOGITS
    MENAFN
    0.77
    AnimationsModule
    0.77
    BeginContext
    0.74
    UVWXYZ
    0.71
    IsMutable
    0.71
    AndEndTag
    0.71
    BufferException
    0.68
     resourceCulture
    0.68
    AndroidJUnit
    0.66
    enumi
    0.66
    Activations Density 0.005%

    No Known Activations