© 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. 43844
    Prev
    Next
    INDEX
    Explanations

    ector

    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
     Senate
    -0.72
     roy
    -0.63
     صوتيه
    -0.60
    ching
    -0.59
     senate
    -0.58
    mology
    -0.57
    Senate
    -0.57
     SENATE
    -0.57
     Roy
    -0.56
    Roy
    -0.54
    POSITIVE LOGITS
    contentLoaded
    0.66
    AndEndTag
    0.65
    GraphicsUnit
    0.63
    hoeddwyd
    0.63
    DebuggerNonUser
    0.63
    oplasma
    0.60
    UnusedPrivate
    0.57
    sidemargin
    0.57
    addCriterion
    0.56
     jadx
    0.55
    Activations Density 0.067%

    No Known Activations