© 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. 15889
    Prev
    Next
    INDEX
    Explanations

    terms related to fractions or parts in a scientific context

    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
    </i>
    -1.05
     Mourinho
    -0.93
     smtplib
    -0.92
    KURZBESCHREIBUNG
    -0.89
     Lilian
    -0.88
     Elisa
    -0.86
     Calais
    -0.84
     SafeMath
    -0.84
    Gates
    -0.83
     resourceCulture
    -0.82
    POSITIVE LOGITS
     fraction
    1.16
     fractions
    1.16
     Fraction
    1.11
     Fractions
    1.06
    Fraction
    0.96
    fraction
    0.92
     Frazier
    0.73
    XK
    0.71
     Frazer
    0.66
    beforeEach
    0.64
    Activations Density 0.012%

    No Known Activations