© 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. 10650
    Prev
    Next
    INDEX
    Explanations

    terms related to concentric and eccentric geometric concepts

    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
    prüche
    -0.82
    Injectable
    -0.72
    bake
    -0.71
    abetes
    -0.70
    dificio
    -0.69
     referenties
    -0.69
    lloworld
    -0.69
    eaway
    -0.68
     Malte
    -0.68
     vorbei
    -0.68
    POSITIVE LOGITS
     Ecc
    1.42
     ecc
    1.34
     eccentricity
    1.30
    Ecc
    1.22
     eccentric
    1.13
    entric
    1.03
    ecc
    0.86
     Rocking
    0.84
    centric
    0.82
     ECC
    0.81
    Activations Density 0.003%

    No Known Activations