© 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. 295
    Prev
    Next
    INDEX
    Explanations

    clauses and question-like structures often including words like "if," "would," "could," "thought," and forms of "be."

    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
     reportedly
    -0.98
     apparently
    -0.94
     seems
    -0.90
     ovviamente
    -0.84
     Apparently
    -0.84
    Apparently
    -0.83
     usually
    -0.82
     seem
    -0.82
     obviously
    -0.81
    apparently
    -0.78
    POSITIVE LOGITS
    GEBURTSDATUM
    1.04
     للمعارف
    0.98
    IsMutable
    0.96
     المعيارى
    0.87
     وأن
    0.84
     algún
    0.84
     فريبيس
    0.81
     algum
    0.81
     abbiano
    0.80
     alguna
    0.79
    Activations Density 4.602%

    No Known Activations