© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6034
    Prev
    Next
    INDEX
    Explanations

    by (contextual linking)

    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
    GraphicsUnit
    -0.70
    InjectMocks
    -0.67
    ंदीखरीदारी
    -0.64
    oredCriteria
    -0.61
    makedirs
    -0.59
    AutoField
    -0.58
    flashdata
    -0.57
    WithIOException
    -0.56
    yatı
    -0.56
    msgTypes
    -0.55
    POSITIVE LOGITS
    DockStyle
    0.69
    TemporalType
    0.61
    بوابة
    0.58
    esgue
    0.58
    AutoModerator
    0.57
     setUser
    0.51
    HasAnnotation
    0.48
     Téléchargez
    0.48
    się
    0.48
     internal
    0.48
    Activations Density 0.002%

    No Known Activations