© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2462
    Prev
    Next
    INDEX
    Explanations

    the

    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
    sidemargin
    -0.59
    Și
    -0.57
    strix
    -0.57
    $'
    -0.54
    AutoScaleMode
    -0.54
    UnusedPrivate
    -0.54
     tartalomajánló
    -0.54
    SequentialGroup
    -0.54
    StructEnd
    -0.54
    PRNewswire
    -0.53
    POSITIVE LOGITS
    uxxxx
    0.79
     level
    0.71
     number
    0.65
    level
    0.58
     degree
    0.57
     use
    0.56
    UIControlState
    0.54
     levels
    0.52
     número
    0.52
    AsUp
    0.50
    Activations Density 0.007%

    No Known Activations