© 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. 30738
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between concepts or entities, particularly 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
     فريبيس
    -0.69
     endforeach
    -0.65
    ]")]
    -0.64
    rungsseite
    -0.63
    __':
    -0.60
     Carro
    -0.55
     surla
    -0.55
    RUnlock
    -0.54
    ++
    -0.54
     coexistence
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.54
    ContentAsync
    0.53
    DeleteBehavior
    0.49
    kosh
    0.48
    AuthProvider
    0.47
    wirkt
    0.44
    withIdentifier
    0.44
    MultipartFile
    0.43
     vapeur
    0.43
    CreateMap
    0.42
    Activations Density 0.130%

    No Known Activations