© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1121
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    kapnya
    -0.57
     Wikiseite
    -0.56
    
    -0.53
     ddelweddau
    -0.53
    PARATUS
    -0.52
    fromnode
    -0.52
    Pratique
    -0.51
     rubbing
    -0.51
     embassy
    -0.49
     perfección
    -0.49
    POSITIVE LOGITS
     as
    0.69
    ParallelGroup
    0.59
     alone
    0.56
    as
    0.50
    لينكات
    0.50
     Alone
    0.49
    GeoNames
    0.48
    úrese
    0.48
    Alone
    0.46
    uchter
    0.46
    Activations Density 0.005%

    No Known Activations