© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 804
    Prev
    Next
    INDEX
    Explanations

    a variety of words and phrases that are related to numbers, equality and setting values (math, stats, computer code)

    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
     متعلقه
    -0.60
    tekend
    -0.52
    Vidite
    -0.52
    Rüyada
    -0.49
    timation
    -0.49
    endforeach
    -0.48
    Sprintf
    -0.47
    ftagPool
    -0.46
    OGND
    -0.45
    ِن
    -0.45
    POSITIVE LOGITS
     zero
    1.19
    zero
    1.05
     equal
    1.01
    值为
    0.99
     Zero
    0.95
     Equal
    0.94
     zeroes
    0.94
     equals
    0.93
    Zero
    0.93
     ZERO
    0.93
    Activations Density 1.727%

    No Known Activations