Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14479
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dislocation" and references to "pan," indicating it detects mentions related to dislocation events or conditions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pan
    -0.68
    uxxxx
    -0.63
    WebControls
    -0.59
    InstanceState
    -0.58
    fällig
    -0.57
     Schall
    -0.54
    bedingt
    -0.53
    بخ
    -0.53
     definit
    -0.53
     spe
    -0.53
    POSITIVE LOGITS
    pan
    1.24
     Bey
    0.74
     Roskov
    0.74
    Bey
    0.70
     agrí
    0.69
    MigrationBuilder
    0.69
    ited
    0.67
    IsContent
    0.63
    Bj
    0.60
     dislocation
    0.59
    Activations Density 0.004%

    No Known Activations