© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 97330
    Prev
    Next
    INDEX
    Explanations

    went

    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
    ^(@)
    -0.73
    !")
    
    -0.71
     nemlig
    -0.70
    ondheim
    -0.67
     électroniques
    -0.65
    ]}"
    -0.65
    $'
    -0.64
     grecque
    -0.64
    `;
    
    -0.62
     avoient
    -0.61
    POSITIVE LOGITS
     thereby
    0.60
    Personensuche
    0.54
     therefrom
    0.52
     hence
    0.50
     thereof
    0.50
     therefore
    0.48
     thus
    0.47
     thereon
    0.47
     therefor
    0.45
     iirc
    0.43
    Activations Density 0.001%

    No Known Activations