© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3600
    Prev
    Next
    INDEX
    Explanations

    A

    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
     or
    -0.45
    thio
    -0.43
     tương
    -0.42
     imp
    -0.41
    _{-}
    -0.39
    пря
    -0.37
    iprot
    -0.36
    4
    -0.36
    9
    -0.36
    емое
    -0.35
    POSITIVE LOGITS
     Мексичка
    0.78
    \{\\
    0.77
    VersionUID
    0.75
     kasarigan
    0.74
     ſche
    0.74
     houſe
    0.73
     ſtate
    0.73
     متعلقه
    0.72
     BoxDecoration
    0.72
     ſtand
    0.71
    Activations Density 0.001%

    No Known Activations