© 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. 24509
    Prev
    Next
    INDEX
    Explanations

    references to individualized approaches or concepts in context

    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
     impieg
    -0.43
    UGE
    -0.42
    TypeInfo
    -0.40
    ous
    -0.40
    ssen
    -0.40
    lesi
    -0.39
    estres
    -0.39
    PRIORITY
    -0.39
     zob
    -0.38
    sung
    -0.38
    POSITIVE LOGITS
    Individual
    1.41
     individual
    1.38
     Individual
    1.31
    individual
    1.30
     INDIVIDUAL
    1.25
     individualized
    1.20
     individually
    1.18
     personal
    1.16
    Individ
    1.13
     individuale
    1.13
    Activations Density 0.395%

    No Known Activations