© 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. 26506
    Prev
    Next
    INDEX
    Explanations

    future tense verbs and phrases indicating possibility or necessity

    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
    
    -0.87
     autorytatywna
    -0.73
    SharedDtor
    -0.73
     referenties
    -0.70
    InstrumentedTest
    -0.68
    antMatchers
    -0.67
    帖最后由
    -0.64
    ectady
    -0.62
     ref
    -0.62
    Autoritní
    -0.62
    POSITIVE LOGITS
     noticed
    0.73
    [++
    0.66
     notice
    0.62
     Zuz
    0.61
     thấy
    0.60
    viste
    0.60
     widać
    0.60
     noticing
    0.59
    descarga
    0.59
    notice
    0.58
    Activations Density 0.046%

    No Known Activations