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. 32094
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or actions in technical contexts

    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
    When
    -0.56
    stonia
    -0.54
    During
    -0.53
     share
    -0.52
    ArgsConstructor
    -0.52
    Every
    -0.51
     During
    -0.51
    νώ
    -0.50
    ναι
    -0.50
    ling
    -0.50
    POSITIVE LOGITS
    OGND
    0.93
    PushMatrix
    0.75
    AndPassword
    0.74
    HostException
    0.71
    Revenir
    0.69
    stateMutability
    0.67
     виправивши
    0.67
     contextLoads
    0.66
    Παραπομπές
    0.66
    \{\\
    0.65
    Activations Density 0.041%

    No Known Activations