© 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. 20295
    Prev
    Next
    INDEX
    Explanations

    propositions and conditions related to assumptions in a theoretical 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
     Mous
    -0.67
    ules
    -0.66
    oia
    -0.65
    ule
    -0.63
    ならず
    -0.61
     Miro
    -0.60
    umes
    -0.58
    ose
    -0.58
    <?
    -0.57
    ular
    -0.57
    POSITIVE LOGITS
    ruptedException
    0.67
    ptonshire
    0.66
     Assumptions
    0.63
    RegressionTest
    0.61
    ArgsConstructor
    0.61
     Numerade
    0.61
    RoutingModule
    0.60
     Assumption
    0.60
     "..\..\..\
    0.60
     UnityEditor
    0.59
    Activations Density 0.019%

    No Known Activations