© 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. 30768
    Prev
    Next
    INDEX
    Explanations

    numerical data associated with probabilities and percentages

    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
    NamedQueries
    -0.46
    kloped
    -0.45
    wahati
    -0.44
     kem
    -0.44
    BB
    -0.44
     Dispatch
    -0.44
    ıdır
    -0.43
    elf
    -0.42
    Tikang
    -0.42
    ivka
    -0.41
    POSITIVE LOGITS
     дописавши
    0.61
     AssemblyCulture
    0.60
    ItemBackground
    0.60
    odeon
    0.60
     parallelism
    0.59
    memoized
    0.58
     reciprocity
    0.57
     betweenstory
    0.56
    });
    0.56
    FieldOffset
    0.55
    Activations Density 0.128%

    No Known Activations