© 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. 42592
    Prev
    Next
    INDEX
    Explanations

    foci

    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
     foci
    -1.04
    ametric
    -0.97
     виправивши
    -0.81
     varandra
    -0.57
     réguli
    -0.57
     jöv
    -0.56
    Aktualisiert
    -0.56
     feroit
    -0.56
     teñ
    -0.56
    SPATH
    -0.55
    POSITIVE LOGITS
    ParallelGroup
    0.54
    intios
    0.53
     positions
    0.52
    aco
    0.52
    eroy
    0.51
    //
    0.49
    mybatisplus
    0.49
    次郎
    0.49
    ropical
    0.47
    romolecules
    0.47
    Activations Density 1.684%

    No Known Activations