© 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. 21684
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment of contributions and support

    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
    Portale
    -0.93
    RenderAtEndOf
    -0.89
     tartalomajánló
    -0.86
     فريبيس
    -0.85
     مشين
    -0.85
     незавершена
    -0.81
    tagHelperRunner
    -0.74
     виправивши
    -0.71
    évaluateur
    -0.70
     HasFactory
    -0.68
    POSITIVE LOGITS
     also
    0.60
    also
    0.53
     επίσης
    0.51
     también
    0.48
    ⊹
    0.48
     أيضًا
    0.47
     again
    0.45
     ferner
    0.45
    égal
    0.45
    これも
    0.45
    Activations Density 0.481%

    No Known Activations