© 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. 0-CLT-HP
    7. 42487
    Prev
    Next
    INDEX
    Explanations

    involved

    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
     Informatics
    -0.52
     [](
    -0.50
     Reaction
    -0.49
     Synthesis
    -0.49
     plasma
    -0.48
     Affecting
    -0.48
    стма
    -0.47
     juiz
    -0.46
     Reactivity
    -0.46
    mrb
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.66
    rungsseite
    0.65
    mogorov
    0.60
     autorytatywna
    0.59
    Демографія
    0.57
     bezeichneter
    0.56
    
    0.56
    Jeografia
    0.54
     незавершена
    0.52
     Dionys
    0.52
    Activations Density 0.101%

    No Known Activations