© 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. 4-CLT-HP
    7. 4510
    Prev
    Next
    INDEX
    Explanations

    self-reference

    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
    mybatisplus
    -0.65
    </caption>
    -0.61
     мәкал
    -0.60
    脚注の使い方
    -0.59
    MessageOf
    -0.58
    ściej
    -0.57
     contd
    -0.57
    '},
    -0.57
    олові
    -0.56
     themſelves
    -0.56
    POSITIVE LOGITS
    ValueStyle
    0.60
    bootstrapcdn
    0.56
     Zar
    0.46
     Kem
    0.45
     assurance
    0.43
     Cam
    0.42
    Physical
    0.42
     Camp
    0.42
    vetica
    0.42
    SequentialGroup
    0.42
    Activations Density 0.001%

    No Known Activations