© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94244
    Prev
    Next
    INDEX
    Explanations

    chemical substances/drugs

    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
    windowFixed
    -0.74
    ագրություններ
    -0.72
    IVEREF
    -0.71
     دیکھیے
    -0.65
    UrlResolution
    -0.63
    COUVER
    -0.61
    @[+][
    -0.59
     surla
    -0.59
    Revenir
    -0.57
     saites
    -0.57
    POSITIVE LOGITS
    osten
    0.52
    ly
    0.49
     Punk
    0.47
     Prior
    0.47
     Top
    0.45
    ty
    0.45
     Kern
    0.45
     Witness
    0.45
     Re
    0.44
     Bur
    0.44
    Activations Density 0.014%

    No Known Activations