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. 25473
    Prev
    Next
    INDEX
    Explanations

    terms related to software and corporate responsibilities

    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
    legd
    -0.49
    /
    -0.49
    druck
    -0.49
     vit
    -0.48
    exact
    -0.48
    compareTo
    -0.48
     final
    -0.47
     exact
    -0.47
    alias
    -0.47
    OLAS
    -0.47
    POSITIVE LOGITS
    ContentAsync
    0.71
     AppCompatTheme
    0.67
     Normdatei
    0.64
    EDEFAULT
    0.64
    migrationBuilder
    0.63
    homonymie
    0.61
    RTDA
    0.61
    pagos
    0.59
    OCCURRED
    0.59
    RuleContext
    0.58
    Activations Density 0.018%

    No Known Activations