© 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. 1-CLT-HP
    7. 15131
    Prev
    Next
    INDEX
    Explanations

    emia

    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
     monoxide
    -0.75
     vált
    -0.50
    emia
    -0.49
     scienza
    -0.47
    wied
    -0.46
     Kohlen
    -0.45
    casio
    -0.44
     coscienza
    -0.44
     almendras
    -0.44
    ритори
    -0.44
    POSITIVE LOGITS
    SharedCtor
    0.68
    Personendaten
    0.68
    Personensuche
    0.66
    httphttps
    0.65
     noDo
    0.64
    tagHelperRunner
    0.61
     estimés
    0.60
    LookAnd
    0.60
    setVerticalGroup
    0.59
    foria
    0.59
    Activations Density 0.021%

    No Known Activations