© 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. 16816
    Prev
    Next
    INDEX
    Explanations

    concepts related to reasoning and intellectual thought processes

    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
    ixel
    -0.57
     Audiodateien
    -0.57
    jsii
    -0.57
     ballet
    -0.52
    twimg
    -0.51
    styleType
    -0.51
    setopt
    -0.50
     totalSupply
    -0.49
    beat
    -0.48
     Kidman
    -0.48
    POSITIVE LOGITS
     supérieures
    0.61
     esprits
    0.59
     MatDialog
    0.57
    acité
    0.56
    wied
    0.56
    ionalmente
    0.54
     Normdatei
    0.53
     superiores
    0.53
    accès
    0.52
     renter
    0.52
    Activations Density 0.012%

    No Known Activations