© 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. 2476
    Prev
    Next
    INDEX
    Explanations

    the word "more," especially "more specifically"

    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
    providedIn
    -0.88
    tagHelperRunner
    -0.85
     createState
    -0.73
    AutoScaleMode
    -0.68
     الدولى
    -0.66
     насељу
    -0.63
    PropertyChanging
    -0.63
     defaultstate
    -0.63
     ब्रेकडाउन
    -0.63
    utilisons
    -0.61
    POSITIVE LOGITS
     specifically
    1.01
     Specifically
    0.93
    Specifically
    0.88
     precisely
    0.87
    specifically
    0.80
     particularly
    0.78
     exactly
    0.77
     precisamente
    0.69
     practically
    0.67
     especific
    0.66
    Activations Density 0.032%

    No Known Activations