© 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. 2-RES-MATRYOSHKA-DC
    7. 3665
    Prev
    Next
    INDEX
    Explanations

    references to ecological or genetic diversity

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.65
     utafitiHapana
    -0.61
    }],
    -0.59
    adaptiveStyles
    -0.59
    ьаж
    -0.59
    ()
    -0.58
    various
    -0.58
    ftagPool
    -0.57
    CreateMap
    -0.57
    **
    -0.56
    POSITIVE LOGITS
     diversity
    2.94
     Diversity
    2.80
    diversity
    2.75
    Diversity
    2.73
     diversidad
    1.80
     diversité
    1.79
    IVERSITY
    1.70
    diverse
    1.68
     Diverse
    1.66
    Diverse
    1.63
    Activations Density 0.010%

    No Known Activations