© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13556
    Prev
    Next
    INDEX
    Explanations

    inject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     injection
    -1.49
     Injection
    -1.38
    injection
    -1.34
     injected
    -1.25
    Injection
    -1.24
     inject
    -1.22
     injecting
    -1.21
     injections
    -1.18
     Inject
    -1.16
    inject
    -1.15
    POSITIVE LOGITS
    rishnan
    0.65
    glEnd
    0.52
     snippetHide
    0.49
    writerow
    0.49
     mał
    0.48
    altor
    0.47
     Crew
    0.45
     šķ
    0.45
    ating
    0.44
     debout
    0.44
    Activations Density 0.038%

    No Known Activations