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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2155
    Prev
    Next
    INDEX
    Explanations

    mentions of injection

    oai_token-act-pair · gemini-2.0-flash
    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
     Gun
    -0.90
     gun
    -0.87
    AsUp
    -0.84
     guns
    -0.77
     bArr
    -0.77
    Gun
    -0.77
    migrationBuilder
    -0.76
    GUN
    -0.75
    gun
    -0.73
     iArr
    -0.73
    POSITIVE LOGITS
     injection
    2.48
     Injection
    2.38
     inject
    2.36
     injected
    2.30
     injecting
    2.17
     Inject
    2.14
    injected
    2.03
    Injection
    2.02
     injections
    2.00
    injection
    2.00
    Activations Density 0.019%

    No Known Activations