© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1263
    Prev
    Next
    INDEX
    Explanations

    the word "not"

    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.22.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.22.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
     anything
    -0.90
    anything
    -0.89
     jemals
    -0.85
     any
    -0.80
    任何
    -0.76
     Any
    -0.75
    Any
    -0.75
    Anything
    -0.74
     Anything
    -0.73
    either
    -0.69
    POSITIVE LOGITS
     only
    1.13
     onely
    0.90
     infrequently
    0.88
    tingham
    0.88
    parsedMessage
    0.85
     مشين
    0.83
    withstanding
    0.80
     surprisingly
    0.77
     forgetting
    0.77
     autorytatywna
    0.77
    Activations Density 0.419%

    No Known Activations