© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 149
    Prev
    Next
    INDEX
    Explanations

    requests for information or assistance

    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
    IntoConstraints
    -0.92
    脚注の使い方
    -0.91
    kuuta
    -0.86
    postcss
    -0.84
     للمعارف
    -0.82
    HomeAsUp
    -0.78
     TestBed
    -0.78
    DataAnnotations
    -0.77
    URLException
    -0.77
    Luong
    -0.76
    POSITIVE LOGITS
     Give
    1.63
    Give
    1.60
     give
    1.55
     gives
    1.52
    give
    1.48
    gives
    1.40
    Gives
    1.38
     gave
    1.35
     Gives
    1.34
     Giving
    1.32
    Activations Density 1.518%

    No Known Activations