Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 17178
    Prev
    Next
    INDEX
    Explanations

    phrases or elements that convey social critique and interaction with audiences

    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
     برانيه
    -0.63
    帖最后由
    -0.60
     esternos
    -0.58
    Rè
    -0.57
    Geografi
    -0.55
     tradução
    -0.53
    setSuccess
    -0.51
    ILayout
    -0.50
     gynhyrchwyd
    -0.50
    Попис
    -0.50
    POSITIVE LOGITS
    ürze
    0.59
     Kenyatta
    0.52
     tartalomajánló
    0.51
     published
    0.50
    liefert
    0.49
     publications
    0.48
     splash
    0.47
    seteq
    0.47
     Published
    0.46
     pictorial
    0.45
    Activations Density 0.558%

    No Known Activations