© 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. 12-RES-MATRYOSHKA-DC
    7. 4677
    Prev
    Next
    INDEX
    Explanations

    repetitive language or variations in negation forms

    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
    Tw
    -0.52
     Neder
    -0.49
     Nib
    -0.47
     Jy
    -0.47
    сту
    -0.47
    copia
    -0.47
    erg
    -0.46
    Unders
    -0.45
     Mej
    -0.45
    zap
    -0.45
    POSITIVE LOGITS
     AssemblyCompany
    0.80
    <bos>
    0.72
    sizeCache
    0.69
    曖昧さ回避
    0.65
    HideFlags
    0.65
     المعيارى
    0.65
    HasBeenSet
    0.64
    matchCondition
    0.63
     تضيفلها
    0.62
    NewUrlParser
    0.62
    Activations Density 0.234%

    No Known Activations