© 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. 21563
    Prev
    Next
    INDEX
    Explanations

    terms related to modifications and outputs in programming functions

    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
     Oakes
    -0.65
    lafen
    -0.60
    økt
    -0.59
    lamic
    -0.57
    InlineData
    -0.57
    Cobra
    -0.57
     médicaux
    -0.56
    schöne
    -0.56
     Beal
    -0.54
     Schenk
    -0.54
    POSITIVE LOGITS
     незавершена
    0.79
    tanleria
    0.75
     defaultstate
    0.74
    Personendaten
    0.70
    RenderAtEndOf
    0.70
    BeginContext
    0.69
    bitField
    0.68
    inout
    0.68
    tagHelperRunner
    0.66
    httphttps
    0.65
    Activations Density 0.014%

    No Known Activations