© 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. 5-CLT-HP
    4. 94765
    Prev
    Next
    INDEX
    Explanations

    staff

    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
    matchCondition
    -0.66
     BoxFit
    -0.63
     wherefore
    -0.59
    rungsseite
    -0.58
    )?;
    -0.57
     nakalista
    -0.57
    []
    
    -0.57
     👎
    -0.56
    protoc
    -0.55
    ')['
    -0.55
    POSITIVE LOGITS
     russes
    0.59
     africain
    0.50
    jut
    0.50
    ároz
    0.45
     Natural
    0.44
    ormais
    0.43
     européen
    0.43
     typically
    0.43
    temun
    0.42
     typelib
    0.42
    Activations Density 0.000%

    No Known Activations