© 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. 20144
    Prev
    Next
    INDEX
    Explanations

    references to vague or nonspecific items and concepts

    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
    reactstrap
    -0.55
     industriales
    -0.50
     lisää
    -0.49
     tekem
    -0.49
     termica
    -0.48
    います
    -0.48
     méta
    -0.47
    みましょう
    -0.46
     antaranya
    -0.46
    contri
    -0.46
    POSITIVE LOGITS
     []:
    0.72
    
    0.71
    avigation
    0.69
    dafx
    0.68
    %)$
    0.66
     surla
    0.66
    ########.
    0.65
    WriteTagHelper
    0.64
    folger
    0.63
    новниш
    0.63
    Activations Density 0.020%

    No Known Activations