© 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. 5517
    Prev
    Next
    INDEX
    Explanations

    technical problems

    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
     OkHttpClient
    -0.56
    ParallelGroup
    -0.56
     haircuts
    -0.53
     rhyming
    -0.52
    Portale
    -0.50
     InputDecoration
    -0.50
    GeneratedValue
    -0.50
    lastTime
    -0.49
    orith
    -0.49
     disbelief
    -0.47
    POSITIVE LOGITS
     be
    0.63
     puisse
    0.56
    EDEFAULT
    0.53
    цездатний
    0.53
    BeginContext
    0.52
     Either
    0.50
    be
    0.50
     essayé
    0.49
    obel
    0.49
    )");
    0.49
    Activations Density 0.000%

    No Known Activations