© 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. 29079
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to band structures and classifications in scientific contexts

    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
    rences
    -0.76
     Läng
    -0.69
     Noe
    -0.68
     Koen
    -0.68
     Rana
    -0.67
    etheless
    -0.65
     Vern
    -0.65
     Guten
    -0.65
     Kön
    -0.64
    (":");
    -0.64
    POSITIVE LOGITS
     bands
    1.53
     Bands
    1.45
    Band
    1.43
     BAND
    1.41
    Bands
    1.38
    BAND
    1.37
     Band
    1.35
    bands
    1.34
     band
    1.31
    band
    1.30
    Activations Density 0.019%

    No Known Activations