© 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. 42970
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    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
     bad
    -0.97
     Bad
    -0.95
    harm
    -0.93
    Bad
    -0.88
    bad
    -0.86
    evil
    -0.86
     harm
    -0.85
     Harmful
    -0.80
     evil
    -0.79
     BAD
    -0.79
    POSITIVE LOGITS
    ers
    0.76
    r
    0.71
    s
    0.68
    u
    0.63
    re
    0.61
    ness
    0.61
    om
    0.60
    m
    0.60
    my
    0.59
    mers
    0.58
    Activations Density 0.040%

    No Known Activations