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. 25968
    Prev
    Next
    INDEX
    Explanations

    references to experimental methods and procedures in scientific research

    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
     Audiodateien
    -0.96
     useAppContext
    -0.94
    GEBURTSDATUM
    -0.93
     BoxDecoration
    -0.90
     فريبيس
    -0.88
    Personensuche
    -0.85
    RenderAtEndOf
    -0.83
     wireType
    -0.83
     createSlice
    -0.82
     onCreateView
    -0.81
    POSITIVE LOGITS
    Integer
    0.47
    ീ
    0.43
    yp
    0.42
    enterio
    0.41
    lder
    0.40
    mu
    0.40
    =%
    0.39
    zep
    0.39
    ken
    0.38
    eris
    0.38
    Activations Density 0.745%

    No Known Activations