© 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. 11800
    Prev
    Next
    INDEX
    Explanations

    instances of systematic reviews and meta-analyses in academic texts

    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
    Péri
    -0.56
    _;
    -0.49
    nob
    -0.44
     from
    -0.44
    InitVars
    -0.43
    >());
    -0.42
     declined
    -0.42
    aba
    -0.42
    kko
    -0.42
    >())
    -0.41
    POSITIVE LOGITS
    expandindo
    0.85
     morire
    0.75
    Pautan
    0.74
     AppBundle
    0.73
     mourir
    0.68
    yntaxException
    0.66
     hidupnya
    0.65
     ActivatedRoute
    0.63
    lotl
    0.61
     digitais
    0.61
    Activations Density 0.007%

    No Known Activations