© 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. 16573
    Prev
    Next
    INDEX
    Explanations

    references to specific data analysis techniques or methods

    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
    rungsseite
    -0.82
    InjectAttribute
    -0.81
     محفوظة
    -0.75
     pinulongan
    -0.74
    PerformLayout
    -0.73
    )$_
    -0.69
    |}{$
    -0.69
     שוליים
    -0.68
    󠁿
    -0.68
    Geplaatst
    -0.66
    POSITIVE LOGITS
     simplicité
    0.50
     kedu
    0.48
    écart
    0.47
    wegg
    0.47
    cuerdo
    0.47
    ainville
    0.45
     olvido
    0.45
     démo
    0.44
    autorest
    0.44
    isNotNull
    0.42
    Activations Density 0.052%

    No Known Activations