© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93198
    Prev
    Next
    INDEX
    Explanations

    actions of changing something

    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
    setVerticalGroup
    -0.63
     Activated
    -0.59
    AndEndTag
    -0.59
     acadé
    -0.58
     Missionary
    -0.57
     deepened
    -0.57
     crdi
    -0.57
     mathematicians
    -0.56
    SPJ
    -0.55
     confocal
    -0.55
    POSITIVE LOGITS
     the
    0.65
     it
    0.62
    گي
    0.61
     can
    0.60
    PyExc
    0.54
    цтва
    0.53
    Przypisy
    0.53
     ch
    0.52
     right
    0.50
    agno
    0.49
    Activations Density 0.048%

    No Known Activations