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. 32097
    Prev
    Next
    INDEX
    Explanations

    structured numerical data, particularly related to statistical metrics or percentages

    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
    MigrationBuilder
    -0.93
     Monfieur
    -0.91
     Theſe
    -0.87
     Efq
    -0.86
     Majefty
    -0.85
     Reſ
    -0.84
     Jefus
    -0.82
     Cæsar
    -0.81
     myſelf
    -0.80
     Мексичка
    -0.79
    POSITIVE LOGITS
    <eos>
    0.57
     No
    0.54
     I
    0.53
     la
    0.48
     A
    0.47
     ver
    0.45
    庶
    0.45
     
    0.45
     TestBed
    0.44
     M
    0.44
    Activations Density 0.294%

    No Known Activations