© 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. 12-RES-MATRYOSHKA-DC
    7. 14634
    Prev
    Next
    INDEX
    Explanations

    phrases indicating diversity and variety

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.85
    ymce
    -0.66
    ?».
    -0.66
     one
    -0.64
     few
    -0.64
    ùa
    -0.64
     numberWith
    -0.63
    tructive
    -0.62
    correre
    -0.62
    eaky
    -0.61
    POSITIVE LOGITS
     Marathi
    0.63
     Kitts
    0.62
     PSOE
    0.62
     frosts
    0.60
     Puglia
    0.60
    UnitTesting
    0.59
     Horizonte
    0.58
     Kraków
    0.57
     Whigs
    0.57
     Hanford
    0.56
    Activations Density 0.028%

    No Known Activations