© 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. 0-CLT-HP
    7. 1386
    Prev
    Next
    INDEX
    Explanations

    pm

    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
     DPM
    -0.66
     PM
    -0.65
     ſche
    -0.65
     contaminated
    -0.60
    Institutional
    -0.60
    sterious
    -0.60
     Efq
    -0.60
    Kinematic
    -0.59
     maxn
    -0.59
     Theſe
    -0.59
    POSITIVE LOGITS
    Personensuche
    0.73
     defaultstate
    0.63
     CreateTagHelper
    0.58
     ویکی‌پدیا
    0.58
    الحياه
    0.54
     '\\;'
    0.54
    Portail
    0.51
    Pipe
    0.50
    RenderAtEndOf
    0.49
     linkovi
    0.49
    Activations Density 0.167%

    No Known Activations