© 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. 5-CLT-HP
    7. 97822
    Prev
    Next
    INDEX
    Explanations

    Typical state

    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
    ReusableCell
    -0.82
     umana
    -0.68
     normales
    -0.66
     normaux
    -0.63
     ordinaires
    -0.61
     normale
    -0.59
     normais
    -0.57
    Personensuche
    -0.57
     malades
    -0.56
     normalement
    -0.56
    POSITIVE LOGITS
    BASEPATH
    0.59
    COUVER
    0.49
    +#+
    0.49
     selves
    0.48
    IsContent
    0.46
    MENAFN
    0.44
    do
    0.44
    rana
    0.43
    peño
    0.43
     ourselves
    0.41
    Activations Density 0.004%

    No Known Activations