© 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. 91168
    Prev
    Next
    INDEX
    Explanations

    hierarchical systems or positions

    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
     faveur
    -0.59
    erweise
    -0.50
     enfans
    -0.46
     riduzione
    -0.45
     vuitton
    -0.45
     successo
    -0.45
    licherweise
    -0.44
    atriz
    -0.44
    alsy
    -0.44
    nadequate
    -0.44
    POSITIVE LOGITS
     to
    0.88
    Geplaatst
    0.71
    MockMvc
    0.67
     gynhyrchwyd
    0.66
    ChildScrollView
    0.65
    存于互联网档案馆
    0.65
    fetchone
    0.60
    AnchorStyles
    0.59
    UnsafeEnabled
    0.59
    Personendaten
    0.56
    Activations Density 0.006%

    No Known Activations