© 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. 4-CLT-HP
    7. 1535
    Prev
    Next
    INDEX
    Explanations

    of

    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
     ivelany
    -0.61
    ่านั้น
    -0.57
     TAMBÉM
    -0.56
    ItemBackground
    -0.56
     Administrativna
    -0.54
    ########.
    -0.53
    sterious
    -0.52
    hoea
    -0.48
     onOptions
    -0.48
     bandoulière
    -0.48
    POSITIVE LOGITS
     knowledge
    0.76
     Knowledge
    0.73
    knowledge
    0.69
     Know
    0.64
    Knowledge
    0.63
    ɵɵ
    0.60
     laws
    0.60
     Work
    0.60
     law
    0.60
     KNOWLEDGE
    0.58
    Activations Density 0.007%

    No Known Activations