© 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. 9839
    Prev
    Next
    INDEX
    Explanations

    variations of the letter 'b' or sequences that contain the letter 'b'

    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
     abstrait
    -0.63
    ]='\
    -0.62
     universel
    -0.57
    ocan
    -0.57
    日閲覧
    -0.56
    amaha
    -0.56
    porus
    -0.56
    enderror
    -0.56
    دانشنامهٔ
    -0.55
    város
    -0.55
    POSITIVE LOGITS
    providedIn
    0.66
     surla
    0.65
     Савезне
    0.64
    spesies
    0.63
     intptr
    0.60
    ":[{
    0.60
    MemoryWarning
    0.59
    ExtendWith
    0.59
    Datuak
    0.57
    Composable
    0.57
    Activations Density 0.005%

    No Known Activations