© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    specific types of fictional characters or entities, particularly those associated with attributes or skills in a fantastical 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
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.59
     UserDetails
    -0.59
     IBOutlet
    -0.58
     retor
    -0.57
    thâu
    -0.57
    ArgsConstructor
    -0.57
     semin
    -0.56
    енча
    -0.55
     continúas
    -0.53
    */].
    -0.53
    POSITIVE LOGITS
     chré
    0.67
     coper
    0.58
     pério
    0.58
     compréhen
    0.57
    ècie
    0.57
     fédé
    0.56
     šķ
    0.56
    ]]
    0.54
    rieux
    0.54
    äiv
    0.54
    Activations Density 0.006%

    No Known Activations