© 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. 24-RES-MATRYOSHKA-DC
    7. 134
    Prev
    Next
    INDEX
    Explanations

    the word "an".

    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.24.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.24.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
    WriteTagHelper
    -0.85
    GEBURTSDATUM
    -0.85
    OGND
    -0.81
    تقاوى
    -0.80
    tagHelperRunner
    -0.78
    principalTable
    -0.71
    setVerticalGroup
    -0.71
     تضيفلها
    -0.70
     ligiloj
    -0.70
     OFDb
    -0.70
    POSITIVE LOGITS
     assortment
    0.63
     array
    0.60
     attempt
    0.59
     alternative
    0.59
     entirely
    0.57
     interesting
    0.57
     excellent
    0.56
     important
    0.55
     example
    0.55
     abundance
    0.55
    Activations Density 1.329%

    No Known Activations