© 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. 29949
    Prev
    Next
    INDEX
    Explanations

    references to companies and their structure in job-related 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
    KommentareTeilen
    -0.60
     PyObject
    -0.57
    󠁮
    -0.56
    Hochspringen
    -0.52
    yorsunuz
    -0.47
    setLayoutManager
    -0.47
    postdata
    -0.46
     CharSequence
    -0.46
     ReactDOM
    -0.46
    yoruz
    -0.45
    POSITIVE LOGITS
     employer
    0.80
     employers
    0.79
     '\\;'
    0.74
    Employer
    0.70
     мәкал
    0.70
    Employers
    0.68
     Employer
    0.64
     ModelExpression
    0.63
    RunAsync
    0.63
     Employers
    0.63
    Activations Density 0.122%

    No Known Activations