© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24907
    Prev
    Next
    INDEX
    Explanations

    character descriptions related to powers and abilities in a narrative context

    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
    Negative Logits
     Tul
    -0.51
    URAL
    -0.48
    \{\\
    -0.48
    czerw
    -0.48
    ímetro
    -0.48
     contextLoads
    -0.47
     reflex
    -0.47
    merie
    -0.47
    IDAS
    -0.47
    >")
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.68
     Familienname
    0.68
    twimg
    0.67
    tagHelperRunner
    0.66
     صوتيه
    0.63
     autorytatywna
    0.62
    ⓧ
    0.61
     evil
    0.60
     sinister
    0.59
     wicked
    0.58
    Activations Density 0.198%

    No Known Activations