© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2945
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     betweenstory
    -0.65
    DockStyle
    -0.53
    Portale
    -0.53
    */}
    -0.49
     ourselves
    -0.49
    těte
    -0.49
    ://$
    -0.48
     propOrder
    -0.48
     protoimpl
    -0.48
     colonists
    -0.48
    POSITIVE LOGITS
    vician
    0.51
     avere
    0.50
     sapere
    0.48
    ynb
    0.48
     każdej
    0.48
    offsetof
    0.47
    ().__
    0.47
    manu
    0.47
    مص
    0.46
     لكل
    0.45
    Activations Density 0.002%

    No Known Activations