© 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. 12-RES-MATRYOSHKA-DC
    7. 18463
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shown."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     _('
    -0.72
    Datuak
    -0.66
    ddy
    -0.64
    dy
    -0.61
    DotNetBar
    -0.59
    dede
    -0.59
     ''),
    -0.59
    (&:
    -0.59
    ivez
    -0.58
    dys
    -0.57
    POSITIVE LOGITS
     AssemblyCulture
    1.05
    findpost
    0.78
    EDEFAULT
    0.73
    ICATED
    0.72
    clusal
    0.72
     propOrder
    0.72
    minecraftforge
    0.69
    speakers
    0.69
    antMatchers
    0.69
     Prit
    0.69
    Activations Density 0.015%

    No Known Activations