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. 28264
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress or fatigue

    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
     themselves
    -0.57
    OPE
    -0.51
     potere
    -0.50
     compaction
    -0.50
     Planned
    -0.50
     époux
    -0.49
     grids
    -0.49
     Ambiental
    -0.48
    grids
    -0.47
     Europeo
    -0.47
    POSITIVE LOGITS
    ########.
    0.65
    RenderAtEndOf
    0.65
    enderror
    0.61
    RegressionTest
    0.61
    IsContent
    0.59
    isContained
    0.57
    InjectAttribute
    0.57
    atiche
    0.56
    openzeppelin
    0.56
     Normdatei
    0.55
    Activations Density 0.001%

    No Known Activations