© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    French/Spanish "pour" or "para"

    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
    ouring
    -0.81
     poured
    -0.78
     Infórmanos
    -0.75
     pour
    -0.65
     pours
    -0.64
     pouring
    -0.59
     as
    -0.58
     for
    -0.58
    ւ
    -0.57
     away
    -0.55
    POSITIVE LOGITS
    Personendaten
    0.65
    ⓧ
    0.64
    setVerticalGroup
    0.52
    `),
    0.52
    Παραπομπές
    0.51
    AnimationsModule
    0.50
    }>;
    0.50
    vician
    0.49
    skosten
    0.47
    ByVersion
    0.47
    Activations Density 0.024%

    No Known Activations