© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12307
    Prev
    Next
    INDEX
    Explanations

    common phrases indicating research interest or attention in scientific contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     reports
    -0.56
     Belum
    -0.54
     obſ
    -0.52
     existing
    -0.52
     Afrique
    -0.52
    complexContent
    -0.50
     established
    -0.49
     Egli
    -0.49
    fag
    -0.49
    wpi
    -0.49
    POSITIVE LOGITS
     Emits
    0.77
    UseVisualStyle
    0.56
    poons
    0.53
    μβρίου
    0.53
     autorytatywna
    0.52
    tdessen
    0.52
    umbledore
    0.51
    EnableWeb
    0.51
    ⓧ
    0.50
    Gambas
    0.50
    Activations Density 0.072%

    No Known Activations