© 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. 4-CLT-HP
    7. 675
    Prev
    Next
    INDEX
    Explanations

    semiconductors

    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
    UserScript
    -0.71
     Paglinawan
    -0.71
    bitField
    -0.69
    AnchorStyles
    -0.69
    tvguidetime
    -0.67
     &___
    -0.66
    LookAnd
    -0.66
    memoized
    -0.66
    MemoryWarning
    -0.63
     createSlice
    -0.62
    POSITIVE LOGITS
     transistor
    0.69
     transistors
    0.61
    oved
    0.52
    پیوند
    0.50
     tweeter
    0.50
     GaAs
    0.50
     Transistor
    0.49
    ेशा
    0.48
    сль
    0.48
    byshev
    0.47
    Activations Density 0.204%

    No Known Activations