© 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. 28888
    Prev
    Next
    INDEX
    Explanations

    expressions related to quality and performance assessments

    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
     متعلقه
    -0.83
     المعيارى
    -0.79
    alyptus
    -0.70
    archiviato
    -0.66
    tdessen
    -0.66
     Preferencias
    -0.64
    lorette
    -0.64
    cellaneous
    -0.63
     CanadaChoose
    -0.63
     pleaſure
    -0.63
    POSITIVE LOGITS
     highly
    0.52
     greatly
    0.50
     very
    0.50
     certainly
    0.50
     extremely
    0.46
     particularly
    0.45
     definitely
    0.44
     sure
    0.43
     especially
    0.43
    極
    0.43
    Activations Density 1.007%

    No Known Activations