© 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. 98043
    Prev
    Next
    INDEX
    Explanations

    len

    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
     AssemblyCompany
    -0.73
    ViewFeatures
    -0.66
     Cientí
    -0.66
    ModelSerializer
    -0.65
    initComponents
    -0.64
     initComponents
    -0.63
     TextAppearance
    -0.60
     Lorca
    -0.60
    DataAnnotations
    -0.60
    Lieferumfang
    -0.59
    POSITIVE LOGITS
    isation
    0.64
    ising
    0.62
    izing
    0.60
    ist
    0.56
    als
    0.54
    ouss
    0.54
    ism
    0.53
    ization
    0.53
    ists
    0.52
    ized
    0.48
    Activations Density 0.007%

    No Known Activations