© 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. 0-CLT-HP
    7. 41484
    Prev
    Next
    INDEX
    Explanations

    reviews and manufacturers

    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
    y
    -0.60
    SequentialGroup
    -0.59
     <<<<<<<<<<<<<<
    -0.53
    ical
    -0.51
    bitField
    -0.51
     EconPapers
    -0.51
    ing
    -0.48
    jspx
    -0.47
    ed
    -0.47
    ful
    -0.47
    POSITIVE LOGITS
    bbene
    0.64
     purpoſe
    0.60
     ſever
    0.59
     censiti
    0.59
    igneur
    0.59
    ároz
    0.58
     eenig
    0.58
     pleaſure
    0.58
     beſt
    0.57
    ChildIndex
    0.57
    Activations Density 0.515%

    No Known Activations