© 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. 22-RES-MATRYOSHKA-DC
    7. 2896
    Prev
    Next
    INDEX
    Explanations

    mostly pronouns, conjunctions and punctuation that connect clauses and phrases, but not determiners such as 'the'.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    Билгалдахарш
    -0.84
     فريبيس
    -0.84
    EndInit
    -0.73
    出版年
    -0.73
    AutoScaleMode
    -0.73
    tagHelperRunner
    -0.72
    DockStyle
    -0.71
    SharedDtor
    -0.69
    verwijspagina
    -0.69
     onAnimation
    -0.69
    POSITIVE LOGITS
     hiring
    2.05
     hire
    1.98
     hired
    1.91
     recruited
    1.87
     hires
    1.84
    Hire
    1.74
     Hire
    1.73
    Hiring
    1.71
     Hiring
    1.71
     recruit
    1.68
    Activations Density 0.675%

    No Known Activations