© 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. 18-RES-MATRYOSHKA-DC
    7. 612
    Prev
    Next
    INDEX
    Explanations

    present tense verbs and related nouns in simple clauses, sometimes preceded by "as" or "to"

    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.18.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.18.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
     avoient
    -0.60
    avaient
    -0.60
    tuvo
    -0.54
     slutt
    -0.54
     tinham
    -0.54
     étoit
    -0.53
    Pris
    -0.52
     automatiques
    -0.52
     inmediata
    -0.52
     hjär
    -0.52
    POSITIVE LOGITS
     prepares
    1.16
     progresses
    1.11
     prepare
    0.97
     nears
    0.94
     continues
    0.92
     progress
    0.89
     grows
    0.87
     continue
    0.85
     progressed
    0.85
     slowly
    0.84
    Activations Density 0.782%

    No Known Activations