© 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. 5-CLT-HP
    7. 5841
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    GEBURTSDATUM
    -0.91
    ]")]
    -0.82
    Portail
    -0.81
    webElementXpaths
    -0.77
    principalTable
    -0.74
    SharedCtor
    -0.72
    basicConfig
    -0.72
    expandindo
    -0.70
    matchCondition
    -0.70
    QMetaType
    -0.68
    POSITIVE LOGITS
     habet
    0.42
    ormais
    0.41
     iArr
    0.41
     enjeux
    0.41
    tuvo
    0.41
     égard
    0.39
    componentWill
    0.39
    yorsunuz
    0.38
    cektir
    0.37
    NewUrlParser
    0.37
    Activations Density 0.028%

    No Known Activations