© 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. 93841
    Prev
    Next
    INDEX
    Explanations

    non

    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
    VersionUID
    -0.81
    )++;
    -0.73
    AddTagHelper
    -0.73
     varandra
    -0.73
    tagHelperRunner
    -0.72
     AssemblyProduct
    -0.71
     كومونز
    -0.71
    UnsafeEnabled
    -0.71
     lenker
    -0.71
     ainfi
    -0.70
    POSITIVE LOGITS
    허
    0.52
     Juga
    0.46
     …
    0.46
    2
    0.42
    softc
    0.41
    3
    0.40
    }^{+\
    0.39
     跳转至
    0.39
     propOrder
    0.38
    usha
    0.37
    Activations Density 0.011%

    No Known Activations