© 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. 3587
    Prev
    Next
    INDEX
    Explanations

    whether

    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
     tryck
    -0.54
     vecka
    -0.52
     veckan
    -0.51
     väli
    -0.50
     respectivos
    -0.48
     lisäksi
    -0.47
     cinquante
    -0.47
     drenaje
    -0.47
     precedentes
    -0.47
     tacón
    -0.46
    POSITIVE LOGITS
     you
    0.87
     due
    0.68
     youre
    0.65
    StoryboardSegue
    0.64
    makeConstraints
    0.63
     your
    0.62
     yours
    0.61
    TagMode
    0.60
     becauſe
    0.60
     selling
    0.60
    Activations Density 0.013%

    No Known Activations