© 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. 4-CLT-HP
    7. 323
    Prev
    Next
    INDEX
    Explanations

    connections

    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
    MLLoader
    -0.91
    最快更新
    -0.62
    MethodManager
    -0.58
     surla
    -0.56
     aDecoder
    -0.56
    İstinadlar
    -0.55
    ellees
    -0.54
     comuniques
    -0.53
     AssemblyCompany
    -0.52
    LookAnd
    -0.52
    POSITIVE LOGITS
     with
    0.90
     to
    0.85
    with
    0.65
     therewith
    0.60
     WITH
    0.52
     With
    0.52
     Accidents
    0.52
    With
    0.52
     defects
    0.52
    tto
    0.51
    Activations Density 0.027%

    No Known Activations