© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21461
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative outcomes or deterioration

    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
     Cleo
    -0.75
     puder
    -0.69
    (&:
    -0.68
     numberWith
    -0.68
     prochaines
    -0.67
    PhysRevD
    -0.67
     subtil
    -0.66
    ">//
    -0.66
    PMailer
    -0.65
     Dinah
    -0.65
    POSITIVE LOGITS
     WOR
    0.92
    Worst
    0.87
     worst
    0.86
     Worst
    0.85
    worst
    0.81
    WOR
    0.79
    EndContext
    0.76
    Worse
    0.76
     worse
    0.74
     Vos
    0.73
    Activations Density 0.005%

    No Known Activations