© 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. 6403
    Prev
    Next
    INDEX
    Explanations

    terms related to "characterization" in various contexts

    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
    abetes
    -0.76
     Louie
    -0.71
    vamente
    -0.71
     Duca
    -0.70
    SDAY
    -0.69
     papyrus
    -0.69
    早就
    -0.68
    AddTagHelper
    -0.68
     Navi
    -0.68
    yce
    -0.66
    POSITIVE LOGITS
     CHARACTER
    1.27
     character
    1.25
     Character
    1.25
    character
    1.22
     characters
    1.17
    CHARACTER
    1.12
     Characters
    1.09
    characters
    1.09
    Character
    1.06
     caractère
    1.00
    Activations Density 0.096%

    No Known Activations