© 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. 1-CLT-HP
    7. 15294
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    BarItem
    -0.52
    EOUS
    -0.51
    steer
    -0.49
    TRIBUTION
    -0.49
     sàng
    -0.48
     suna
    -0.48
    pede
    -0.47
    blades
    -0.47
    FieldDescriptor
    -0.46
    edoc
    -0.46
    POSITIVE LOGITS
    Diweddarwch
    0.65
     HasFactory
    0.64
     bezeichneter
    0.62
    IUrlHelper
    0.60
    ')):
    0.58
    contentLoaded
    0.58
     referenties
    0.58
    InjectAttribute
    0.57
    WithIOException
    0.56
    LookAnd
    0.56
    Activations Density 0.152%

    No Known Activations