© 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. 5-CLT-HP
    7. 5636
    Prev
    Next
    INDEX
    Explanations

    coding

    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
     saites
    -0.57
     HasFactory
    -0.55
     esternos
    -0.52
     đài
    -0.51
     виправивши
    -0.50
     match
    -0.50
     }{\
    -0.49
    MLLoader
    -0.49
    Newswire
    -0.49
    urangan
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.61
    IMPORTED
    0.56
    warzys
    0.52
    simpleType
    0.52
    MemoryWarning
    0.50
    kháu
    0.50
    oa̍t
    0.49
    awtextra
    0.49
    membered
    0.49
    EMA
    0.49
    Activations Density 0.001%

    No Known Activations