© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2871
    Prev
    Next
    INDEX
    Explanations

    words that are subjective or of emotional affect

    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
     parce
    -0.60
     lenker
    -0.60
    IUrlHelper
    -0.57
     tantôt
    -0.56
    了吗
    -0.54
    GenerationType
    -0.53
     porque
    -0.53
    ientí
    -0.52
    是因為
    -0.52
    porque
    -0.51
    POSITIVE LOGITS
     considering
    2.20
    considering
    2.06
     Considering
    1.84
    Considering
    1.80
     given
    1.70
     considerando
    1.56
    given
    1.48
     учиты
    1.41
    Given
    1.34
     Given
    1.34
    Activations Density 0.415%

    No Known Activations