© 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. 10030
    Prev
    Next
    INDEX
    Explanations

    stick bean

    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
     Bean
    -1.03
    bean
    -0.94
     bean
    -0.89
    stick
    -0.84
     stick
    -0.84
    Bean
    -0.84
     Stick
    -0.81
    Stick
    -0.79
    الحياه
    -0.74
    BEAN
    -0.69
    POSITIVE LOGITS
    CPtr
    0.49
    ">:
    0.46
     Préférences
    0.43
     Artur
    0.43
     PyTuple
    0.42
     Sandro
    0.41
    MigrationBuilder
    0.41
    NavigationView
    0.41
     cores
    0.40
     Pires
    0.40
    Activations Density 0.033%

    No Known Activations