© 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. 0-CLT-HP
    7. 42457
    Prev
    Next
    INDEX
    Explanations

    negative emotions/situations

    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
     CreateTagHelper
    -1.04
    帖最后由
    -1.04
    ++
    -0.95
    IsMutable
    -0.94
    WithIOException
    -0.94
    AndEndTag
    -0.93
    PreInfinity
    -0.90
    findpost
    -0.88
    \{\\
    -0.85
     Мексичка
    -0.85
    POSITIVE LOGITS
    ly
    2.08
    LY
    1.22
    ally
    1.09
    ness
    1.02
    fully
    0.94
    mente
    0.91
    ed
    0.84
    less
    0.82
    ALLY
    0.80
    了
    0.80
    Activations Density 0.566%

    No Known Activations