© 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. 16813
    Prev
    Next
    INDEX
    Explanations

    measurements in micrometers

    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
     Peralta
    -0.65
    eux
    -0.60
    ArgsConstructor
    -0.58
     throwable
    -0.58
    yordu
    -0.57
    isDebugEnabled
    -0.56
    Bong
    -0.56
    AxisAlignment
    -0.56
    oine
    -0.56
    ífer
    -0.55
    POSITIVE LOGITS
    تقاوى
    0.70
    évaluateur
    0.68
    Tikang
    0.65
     utafitiHapana
    0.65
     AttributeSet
    0.64
    intios
    0.62
    ValueGeneration
    0.61
     AssemblyCulture
    0.59
     متعلقه
    0.59
    isContained
    0.59
    Activations Density 0.003%

    No Known Activations