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. 16
    Prev
    Next
    INDEX
    Explanations

    terms related to errors or exceptions in programming 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
    excellents
    -0.54
    assertNotNull
    -0.53
     rendel
    -0.53
    poň
    -0.52
    glMatrixMode
    -0.52
    Cyfeiriadau
    -0.50
    mær
    -0.49
     pełni
    -0.49
    GetMapping
    -0.49
     zugel
    -0.48
    POSITIVE LOGITS
    TargetException
    0.82
     caused
    0.82
     worse
    0.78
     inflicted
    0.78
     damage
    0.75
    CastException
    0.74
     NSError
    0.71
     attacks
    0.70
    Worse
    0.70
    JSONException
    0.70
    Activations Density 14.506%

    No Known Activations