© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1353
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "almost" followed by numbers or fractions

    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
     <=",
    -0.81
    approximately
    -0.75
     GenerationType
    -0.75
    Autoritní
    -0.73
    Portale
    -0.72
     Relatively
    -0.71
    expandindo
    -0.70
     approximately
    -0.68
    大約
    -0.66
     beginnetje
    -0.65
    POSITIVE LOGITS
     half
    1.14
     halfway
    0.99
     doubling
    0.86
    Half
    0.83
     HALF
    0.83
     halve
    0.80
     halved
    0.80
     doubled
    0.78
    half
    0.77
     Half
    0.76
    Activations Density 0.523%

    No Known Activations