© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16131
    Prev
    Next
    INDEX
    Explanations

    the concept of "phantom" in various contexts

    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
    apore
    -0.70
    ScopeManager
    -0.70
    idorm
    -0.69
     مرئيه
    -0.68
     }}-
    -0.65
    )}-
    -0.64
    oporosis
    -0.63
    =$?
    -0.63
    lgari
    -0.61
    /}.
    -0.60
    POSITIVE LOGITS
    phantom
    1.64
     phantom
    0.79
    Phantom
    0.78
     Phantom
    0.71
     GenerationType
    0.66
    InSection
    0.58
    AddTagHelper
    0.57
    ldb
    0.57
     blest
    0.56
     dimenti
    0.54
    Activations Density 0.000%

    No Known Activations