© 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. 15938
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical references or values

    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
     nahilalakip
    -0.90
    ])).
    -0.72
     disambiguazione
    -0.68
    ]));
    -0.65
    WithMany
    -0.63
    Vidite
    -0.63
    Bleeding
    -0.62
     isSet
    -0.61
     ivelany
    -0.61
     ErrInvalid
    -0.61
    POSITIVE LOGITS
    正直
    0.52
    miary
    0.49
    ConstraintMaker
    0.48
     فريبيس
    0.47
     nationaux
    0.46
    анс
    0.45
     assistir
    0.44
     quedarse
    0.44
    ram
    0.44
    いえば
    0.44
    Activations Density 0.005%

    No Known Activations