© 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. 15111
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ffer
    -1.80
    FFER
    -1.55
    ffers
    -1.20
    ffering
    -1.13
    ffered
    -0.98
    TagMode
    -0.79
    rika
    -0.66
    
    -0.64
     protoimpl
    -0.63
    OGND
    -0.61
    POSITIVE LOGITS
     punte
    0.51
     Hob
    0.50
     seuls
    0.50
     sej
    0.49
    angsaan
    0.48
    ặn
    0.48
     HOB
    0.48
     sanitaires
    0.48
     Congrès
    0.48
     motore
    0.47
    Activations Density 0.022%

    No Known Activations