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. 10119
    Prev
    Next
    INDEX
    Explanations

    formal sign-offs or salutations in written correspondence

    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
     autorytatywna
    -0.57
     חיצוניים
    -0.56
    gatsby
    -0.53
     initComponents
    -0.53
    外部リンク
    -0.52
    وله
    -0.52
    FunctionFlags
    -0.49
     saites
    -0.48
    日閲覧
    -0.48
    AndEndTag
    -0.47
    POSITIVE LOGITS
     Efq
    0.82
     betweenstory
    0.77
     Bourgoin
    0.76
    UnsafeEnabled
    0.71
     Baillargeon
    0.70
    SerializedSize
    0.67
     HttpNotFound
    0.67
     Référence
    0.66
    #+#
    0.65
     reaſon
    0.65
    Activations Density 0.677%

    No Known Activations