© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93651
    Prev
    Next
    INDEX
    Explanations

    value

    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
    ”
    -1.32
     [
    -1.30
    ,”
    -1.09
    ?”
    -1.08
    .”
    -1.08
    ”,
    -1.05
    ”.
    -1.05
    "]
    -1.02
    []"
    -0.96
    ...”
    -0.96
    POSITIVE LOGITS
     “
    1.17
    </h3>
    1.16
     "
    1.13
    expandindo
    1.12
    GEBURTSDATUM
    1.07
    </h6>
    1.02
    ']))
    
    1.02
    '])){
    
    0.97
    '},
    
    0.96
    .)}
    0.96
    Activations Density 0.194%

    No Known Activations