© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    Use

    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
    ++]=
    -0.52
    ROLL
    -0.48
    AfterClass
    -0.48
     straips
    -0.46
     jPanel
    -0.46
     г
    -0.45
    ROLLER
    -0.45
    onne
    -0.45
     fond
    -0.45
    ween
    -0.45
    POSITIVE LOGITS
    fulness
    0.98
     récents
    0.77
     refusé
    0.75
     répon
    0.69
     dépens
    0.68
     ingår
    0.68
     actuels
    0.66
     réserve
    0.66
    seamnă
    0.65
     cervello
    0.65
    Activations Density 0.006%

    No Known Activations