© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1809
    Prev
    Next
    INDEX
    Explanations

    grow

    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
     ujednoznacz
    -0.71
    IntoConstraints
    -0.69
     kasarigan
    -0.64
    ConstraintMaker
    -0.62
    存于互联网档案馆
    -0.59
    Източници
    -0.56
    INSEE
    -0.54
     PublicKey
    -0.54
    kmale
    -0.53
     concurrency
    -0.53
    POSITIVE LOGITS
     suspicious
    0.57
     wireType
    0.53
     rich
    0.52
    DockStyle
    0.52
    تقاوى
    0.51
     gammel
    0.50
     old
    0.50
     Мексичка
    0.49
     accus
    0.48
     pale
    0.47
    Activations Density 0.020%

    No Known Activations