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. 20902
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to disappointment and hope

    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
     Jefus
    -1.17
     purpoſe
    -1.13
     itſelf
    -1.08
     Theſe
    -1.05
     houſe
    -1.04
     poffe
    -1.03
     raiſ
    -1.01
     faſt
    -0.96
     myſelf
    -0.96
     againſt
    -0.96
    POSITIVE LOGITS
    app
    0.52
    /
    0.50
     See
    0.48
     my
    0.47
     or
    0.47
    Se
    0.47
    ↵
    0.47
     people
    0.47
     et
    0.46
     Re
    0.46
    Activations Density 0.375%

    No Known Activations