© 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. 544
    Prev
    Next
    INDEX
    Explanations

    measuring

    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
     HomeComponent
    -0.65
    abestanden
    -0.62
    rajz
    -0.61
     للاسماء
    -0.61
     suivantes
    -0.60
     světa
    -0.60
     Rhymes
    -0.59
     suivants
    -0.59
     rapides
    -0.58
     eccell
    -0.57
    POSITIVE LOGITS
    TargetException
    0.56
    avad
    0.51
     stick
    0.47
     systems
    0.45
     Vikipedi
    0.44
     tape
    0.44
    ագրություններ
    0.43
     wheel
    0.43
     Stick
    0.42
    Wig
    0.41
    Activations Density 0.003%

    No Known Activations