© 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. 98205
    Prev
    Next
    INDEX
    Explanations

    marine

    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
    Jereo
    -0.68
    impianto
    -0.63
     fevere
    -0.63
     pleaſure
    -0.62
     Ause
    -0.62
     Houſe
    -0.61
    neſs
    -0.61
    исленность
    -0.60
     purpoſe
    -0.60
    principalTable
    -0.60
    POSITIVE LOGITS
     con
    0.46
    ürt
    0.46
    c
    0.45
     kasarigan
    0.44
    levé
    0.44
    OBJECT
    0.43
    fot
    0.43
    carat
    0.43
     обез
    0.43
    ibol
    0.42
    Activations Density 0.001%

    No Known Activations