© 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. 1-CLT-HP
    7. 14329
    Prev
    Next
    INDEX
    Explanations

    ically

    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
    ically
    -0.78
     Савезне
    -0.75
    GenerationType
    -0.60
    ($__
    -0.60
     Privacidade
    -0.60
    Биография
    -0.56
    $}}
    -0.55
    XmlAccessorType
    -0.53
     reír
    -0.52
     जबकि
    -0.51
    POSITIVE LOGITS
     Bioaccumulative
    0.60
     éclair
    0.55
    GEBURTS
    0.55
    AndEndTag
    0.53
    AutoScale
    0.52
     Assertion
    0.50
     Screens
    0.49
     Beck
    0.49
     Paving
    0.49
    uoco
    0.48
    Activations Density 0.010%

    No Known Activations