© 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. 30632
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or applications of something

    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
    UnusedPrivate
    -0.69
    stdc
    -0.68
    تقاوى
    -0.66
    httphttps
    -0.65
    thenReturn
    -0.62
     BrowserModule
    -0.61
    tikzpicture
    -0.61
    Personendaten
    -0.61
     staying
    -0.60
    gdx
    -0.60
    POSITIVE LOGITS
    asaan
    0.65
    Bisous
    0.60
     aufs
    0.60
    ERTE
    0.59
     consultato
    0.58
    bagno
    0.57
    Respectfully
    0.56
     Valladolid
    0.54
    Herzlich
    0.54
    Suisse
    0.54
    Activations Density 0.044%

    No Known Activations