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. 25516
    Prev
    Next
    INDEX
    Explanations

    the presence of specific phrases or titles

    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
     المعيارى
    -1.02
    
    -0.82
    Datuak
    -0.75
    RegistryLite
    -0.73
    GraphicsUnit
    -0.72
    principalTable
    -0.69
    EndContext
    -0.69
    migrationBuilder
    -0.63
    رشف
    -0.63
    Personendaten
    -0.62
    POSITIVE LOGITS
    AppRoutingModule
    0.59
    BrowserModule
    0.58
     ✭✭
    0.49
     Aussch
    0.49
     bgcolor
    0.48
    Здра
    0.47
    UpdateCommand
    0.46
    ificent
    0.45
    kuva
    0.45
     '''
    0.45
    Activations Density 0.000%

    No Known Activations