© 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. 23593
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or direction involving 'up' and 'down'

    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
    awtextra
    -0.72
    })();
    -0.65
     intptr
    -0.63
     around
    -0.57
     autorytatywna
    -0.57
     oko
    -0.56
    antaine
    -0.55
    ionali
    -0.54
     Abo
    -0.54
     שוליים
    -0.54
    POSITIVE LOGITS
    ftagPool
    0.98
    دانشنامهٔ
    0.81
    ConfigureAwait
    0.81
    UIControlState
    0.77
    mybatisplus
    0.71
    ModelAdmin
    0.69
    PostInfinity
    0.68
    tagHelperRunner
    0.68
    MigrationBuilder
    0.68
    FieldDescriptor
    0.67
    Activations Density 0.019%

    No Known Activations