© 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. 31926
    Prev
    Next
    INDEX
    Explanations

    key terms related to investigations and evidence evaluation

    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
    GraphicsUnit
    -0.69
     ويكيميديا
    -0.64
    PhysRevD
    -0.61
     mxArray
    -0.59
     resourceCulture
    -0.57
     linkovi
    -0.56
     incomplète
    -0.54
     DbType
    -0.52
     AssemblyVersion
    -0.51
    InstrumentedTest
    -0.51
    POSITIVE LOGITS
    anyway
    0.54
     anyway
    0.53
     regardless
    0.52
    ldquo
    0.51
     independently
    0.51
    UBE
    0.51
    NameInMap
    0.51
    nip
    0.50
    Anyway
    0.48
     anyways
    0.47
    Activations Density 0.326%

    No Known Activations