© 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. 92208
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    icles
    -1.09
    icle
    -1.08
     inlet
    -0.90
     Inlet
    -0.74
    lt
    -0.61
     inlets
    -0.57
     coucher
    -0.57
    SerializedSize
    -0.52
     It
    -0.50
    etCode
    -0.50
    POSITIVE LOGITS
    Datuak
    0.71
    XmlAccessType
    0.64
     nahilalakip
    0.64
    ValueStyle
    0.63
    featureID
    0.59
     ddelweddau
    0.59
    wpi
    0.59
     '\\;'
    0.59
    WriteLiteral
    0.58
     Chwiliwch
    0.55
    Activations Density 1.246%

    No Known Activations