© 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. 5-CLT-HP
    7. 5565
    Prev
    Next
    INDEX
    Explanations

    alternatives

    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
     alternativa
    -0.72
     alternatives
    -0.71
     alternatif
    -0.69
     alternative
    -0.68
    alternatives
    -0.66
     ALTERNATIVE
    -0.63
    Alternative
    -0.63
    Alternate
    -0.60
     альтерна
    -0.60
     alternativas
    -0.59
    POSITIVE LOGITS
    SequentialGroup
    0.63
    mybatisplus
    0.55
     Roskov
    0.52
     впер
    0.50
     vulgaires
    0.49
     prohibido
    0.49
    辖
    0.48
    Etimología
    0.48
    Hentet
    0.47
    AndroidJUnit
    0.47
    Activations Density 0.011%

    No Known Activations