© 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. 443
    Prev
    Next
    INDEX
    Explanations

    Text segments

    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
    Diweddarwch
    -0.47
     TextAppearance
    -0.47
     continúas
    -0.44
    ემ
    -0.43
     considérons
    -0.43
     capacitive
    -0.42
     виправивши
    -0.42
     gourd
    -0.42
     natural
    -0.41
    Parcelize
    -0.41
    POSITIVE LOGITS
    stdc
    0.75
    EndContext
    0.69
    featureID
    0.63
    httphttps
    0.63
    sizeCache
    0.63
     للمعارف
    0.63
    WithIOException
    0.62
    MessageTagHelper
    0.62
     referenties
    0.61
     CreateTagHelper
    0.60
    Activations Density 0.009%

    No Known Activations