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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91189
    Prev
    Next
    INDEX
    Explanations

    aki

    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
    aki
    -1.56
    AKI
    -1.13
     pinulongan
    -0.96
    Personensuche
    -0.77
    taki
    -0.74
    lech
    -0.72
    ResumeLayout
    -0.70
    脚注の使い方
    -0.70
    tanleria
    -0.65
    jgl
    -0.60
    POSITIVE LOGITS
     [*]
    0.54
     humains
    0.50
    nių
    0.50
    //
    0.49
     madres
    0.49
     connus
    0.48
     mukaan
    0.47
    wę
    0.47
     humanas
    0.46
     symboles
    0.46
    Activations Density 0.095%

    No Known Activations