© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    Code and environment

    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
    ven
    -0.41
    bo
    -0.40
    stre
    -0.39
    lie
    -0.39
    labelledby
    -0.39
    my
    -0.38
    laring
    -0.38
     apre
    -0.38
    bion
    -0.37
    mando
    -0.37
    POSITIVE LOGITS
    IsMutable
    0.71
    RenderAtEndOf
    0.69
     Signalez
    0.69
    fjspx
    0.68
     noDo
    0.68
    AsUp
    0.68
     propOrder
    0.68
     bezeichneter
    0.67
    monary
    0.66
    Datuak
    0.66
    Activations Density 0.001%

    No Known Activations