© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    kes

    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
    Geplaatst
    -1.07
    XmlEnum
    -0.73
     kasarigan
    -0.71
    fjspx
    -0.68
     autorytatywna
    -0.68
    })();
    -0.68
    featureID
    -0.67
     Roskov
    -0.67
    TypedDataSet
    -0.66
    IUrlHelper
    -0.66
    POSITIVE LOGITS
     mashed
    0.40
    ophys
    0.36
     Forth
    0.35
     sánh
    0.34
     liquidation
    0.33
    mbals
    0.33
    tester
    0.32
     sociale
    0.32
     Liquidity
    0.32
    supp
    0.31
    Activations Density 0.004%

    No Known Activations