© 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. 92163
    Prev
    Next
    INDEX
    Explanations

    suitable, appropriate

    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
     Fes
    -0.57
    Шаг
    -0.54
     Bonneville
    -0.53
    omy
    -0.53
    enough
    -0.53
     ostavi
    -0.52
     nors
    -0.51
     Theſe
    -0.50
     Enough
    -0.50
     Zay
    -0.49
    POSITIVE LOGITS
    oredCriteria
    0.63
    سمبر
    0.61
    WithIOException
    0.59
    Ecotoxicity
    0.57
     to
    0.56
     for
    0.53
    MemoryWarning
    0.53
    sidemargin
    0.52
     οποίο
    0.50
    körper
    0.49
    Activations Density 0.052%

    No Known Activations