© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3000
    Prev
    Next
    INDEX
    Explanations

    mathematical solutions and proofs related to formal equations and properties

    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
     wireType
    -0.65
    '}),
    -0.61
    EndContext
    -0.60
    contentLoaded
    -0.59
    AccessorTable
    -0.59
    IntoConstraints
    -0.57
    addContainerGap
    -0.57
    IVEREF
    -0.56
    Rüyada
    -0.56
    Aholisi
    -0.55
    POSITIVE LOGITS
     spørs
    0.55
    ettbewer
    0.54
     Masyarakat
    0.54
    vė
    0.53
    ospels
    0.52
     remplissage
    0.52
    تفصیلات
    0.52
     päivä
    0.52
    各项
    0.51
     remplir
    0.51
    Activations Density 1.068%

    No Known Activations