© 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. 2249
    Prev
    Next
    INDEX
    Explanations

    comparative language indicating expectations or evaluations

    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
    principalColumn
    -0.78
     snippetHide
    -0.76
     للمعارف
    -0.69
    ⓧ
    -0.65
    ngdoc
    -0.59
    ArrowToggle
    -0.59
     مرئيه
    -0.59
     GenerationType
    -0.58
    posedge
    -0.58
     ostavi
    -0.57
    POSITIVE LOGITS
     myſelf
    0.66
     himſelf
    0.61
     themſelves
    0.60
     Theſe
    0.60
     itſelf
    0.57
     becauſe
    0.56
     cauſe
    0.54
    moreland
    0.53
     possibile
    0.52
     reaſon
    0.50
    Activations Density 0.145%

    No Known Activations