© 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. 25358
    Prev
    Next
    INDEX
    Explanations

    terms that denote varying degrees of intensity or magnitude

    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
    SharedCtor
    -0.80
     disambiguazione
    -0.77
    providedIn
    -0.68
     CURIAM
    -0.66
    devise
    -0.65
    />";
    -0.62
    ModelForm
    -0.61
     zuges
    -0.61
    Искәрмәләр
    -0.60
    Yaw
    -0.60
    POSITIVE LOGITS
    archiviato
    0.54
    JspWriter
    0.52
     slim
    0.51
    раздо
    0.51
     Signalez
    0.50
    榄
    0.50
     wesentlich
    0.49
     stationnement
    0.49
     PROCEDURES
    0.48
     safer
    0.48
    Activations Density 0.019%

    No Known Activations