© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 183
    Prev
    Next
    INDEX
    Explanations

    Shang

    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
    WithIOException
    -0.55
    amssymb
    -0.54
    xtext
    -0.53
    MemoryWarning
    -0.52
    posedge
    -0.50
    bobox
    -0.49
    trecht
    -0.49
     Menon
    -0.49
    matchCondition
    -0.49
    HomeAsUpEnabled
    -0.49
    POSITIVE LOGITS
    ri
    0.62
     transfieras
    0.60
    rila
    0.59
     grå
    0.54
    //
    0.50
    StoreMessageInfo
    0.50
    extAlignment
    0.49
     Hola
    0.49
    UnsafeEnabled
    0.49
     følge
    0.49
    Activations Density 0.001%

    No Known Activations