© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16064
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or measurements in a scientific context

    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
     juridiques
    -0.65
     présidenti
    -0.63
     mourut
    -0.61
     ambientale
    -0.60
    thenReturn
    -0.58
     giudi
    -0.57
     anglaise
    -0.54
     judiciaire
    -0.54
     sanitaires
    -0.54
     scolaires
    -0.53
    POSITIVE LOGITS
     насељу
    0.79
    GeneratedCode
    0.69
    MENAFN
    0.67
     arşivlendi
    0.65
    #+#
    0.65
    IVEREF
    0.64
     trav
    0.62
    enumii
    0.61
    addCriterion
    0.61
    ⓧ
    0.60
    Activations Density 0.001%

    No Known Activations