© 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. 29874
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values, specifically prime and composite numbers

    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
    IsMutable
    -0.56
    jach
    -0.53
    dub
    -0.52
    atura
    -0.52
    ртка
    -0.52
    inte
    -0.51
     '
    -0.50
     Marian
    -0.49
     beginnetje
    -0.49
     critical
    -0.49
    POSITIVE LOGITS
    Ivo
    0.66
    THISDAY
    0.65
     ISNI
    0.65
     isInitialized
    0.63
     Poles
    0.63
    crollView
    0.63
    AnimationsModule
    0.62
     Swaziland
    0.62
    Lähteet
    0.60
     يتيمه
    0.60
    Activations Density 0.001%

    No Known Activations