© 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. 0-CLT-HP
    7. 94945
    Prev
    Next
    INDEX
    Explanations

    bei

    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
    nei
    -0.86
    Архівовано
    -0.73
    bei
    -0.68
     arbit
    -0.60
     nei
    -0.56
    stdc
    -0.54
    脚注の使い方
    -0.54
     personnaliser
    -0.53
     yii
    -0.51
    isla
    -0.50
    POSITIVE LOGITS
    SpringBootTest
    0.62
    ChildScrollView
    0.62
     defStyleAttr
    0.56
    s
    0.56
    ContentLoaded
    0.55
     SEDS
    0.53
    Personensuche
    0.52
    AutoField
    0.52
    ForValue
    0.52
    setVerticalGroup
    0.51
    Activations Density 0.152%

    No Known Activations