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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19145
    Prev
    Next
    INDEX
    Explanations

    negative values or low ratings

    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
     sèche
    -0.67
     []:
    -0.54
     paille
    -0.54
     vägen
    -0.53
     flé
    -0.50
     excès
    -0.49
     SwiftUI
    -0.48
     spirituale
    -0.48
     celos
    -0.48
     certify
    -0.47
    POSITIVE LOGITS
     invokingState
    0.66
    ')):
    0.61
    SequentialGroup
    0.60
    prefixer
    0.60
    journals
    0.55
    RTLI
    0.55
    outWeight
    0.55
     informée
    0.54
    Portale
    0.52
    '},
    0.52
    Activations Density 0.006%

    No Known Activations