© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 448
    Prev
    Next
    INDEX
    Explanations

    negative sentiment and strong emotional responses.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    +#+#
    -1.02
     nakalista
    -0.88
    endphp
    -0.88
    tableFuture
    -0.85
    帖最后由
    -0.84
    GenerationType
    -0.81
    ंदीखरीदारी
    -0.81
    GraphicsUnit
    -0.79
    //
    -0.78
    XmlAccessType
    -0.76
    POSITIVE LOGITS
     myſelf
    1.16
     themſelves
    1.09
     himſelf
    1.03
     itſelf
    1.03
     doubtnut
    0.99
     pleaſure
    0.92
     ―――――
    0.91
     fevere
    0.90
     raiſ
    0.89
     ſeveral
    0.86
    Activations Density 7.481%

    No Known Activations