© 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. 41025
    Prev
    Next
    INDEX
    Explanations

    hyster or outpatient

    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
    standers
    -0.72
     AssemblyTitle
    -0.70
    Demografie
    -0.66
    ticus
    -0.65
    dafx
    -0.63
    SharedCtor
    -0.63
     Seventeenth
    -0.61
    rzost
    -0.60
     doubtnut
    -0.60
    parole
    -0.60
    POSITIVE LOGITS
    i
    0.63
    a
    0.60
    oe
    0.59
    ei
    0.58
    ยว
    0.54
    e
    0.54
    eas
    0.52
    ien
    0.51
    ii
    0.50
    o
    0.50
    Activations Density 0.098%

    No Known Activations