© 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. 20-CLT-HP
    7. 72750
    Prev
    Next
    INDEX
    Explanations

    oil wells

    np_max-act-logits · 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
    ary
    -0.59
    ARY
    -0.53
     незавершена
    -0.51
    alty
    -0.50
    ngOnInit
    -0.49
    forName
    -0.46
     ujednoznacz
    -0.46
    Kanpo
    -0.46
    /***/
    -0.45
    onViewCreated
    -0.44
    POSITIVE LOGITS
     Jordi
    0.54
    GIVEREF
    0.53
    évaluateur
    0.53
     Wiktionnaire
    0.52
     uVar
    0.52
     Xmas
    0.52
    WriteTagHelper
    0.52
    okolade
    0.52
    matchCondition
    0.51
    kill
    0.51
    Activations Density 0.005%

    No Known Activations