© 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. 5784
    Prev
    Next
    INDEX
    Explanations

    file paths and directory structures related to SSH configurations

    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
     InputDecoration
    -0.56
     Minato
    -0.55
     الاطلاع
    -0.54
     stamens
    -0.53
     Viti
    -0.53
     незавершена
    -0.52
    мак
    -0.52
     poiv
    -0.51
    reiter
    -0.50
    人心
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.85
    RUnlock
    0.73
    windowFixed
    0.70
    lgari
    0.68
     esternos
    0.67
    edos
    0.66
    ThemeOverlay
    0.64
     Administrativna
    0.64
    舺
    0.60
    MessageOf
    0.59
    Activations Density 0.104%

    No Known Activations