© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76511
    Prev
    Next
    INDEX
    Explanations

    Code/Names with colons

    np_max-act-logits · 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
    WithIOException
    -0.70
     تضيفلها
    -0.53
    extAlignment
    -0.52
     Ent
    -0.39
    GRASS
    -0.38
    encia
    -0.38
    霸
    -0.38
     Whittaker
    -0.36
     Las
    -0.36
     Gras
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.87
    tagHelperRunner
    0.70
    DrawerToggle
    0.64
     tartalomajánló
    0.60
    
    0.60
     transfieras
    0.59
    StoryboardSegue
    0.59
    NameInMap
    0.59
     TextAppearance
    0.58
    InitStruct
    0.58
    Activations Density 0.006%

    No Known Activations