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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97632
    Prev
    Next
    INDEX
    Explanations

    negative events/feelings

    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
    OGND
    -0.96
    TypedDataSet
    -0.89
     Efq
    -0.89
    IsContent
    -0.85
     panic
    -0.85
     Panic
    -0.83
    ConstraintMaker
    -0.82
    NewUrlParser
    -0.81
     panicked
    -0.81
     Theſe
    -0.81
    POSITIVE LOGITS
    .
    0.62
     and
    0.52
    be
    0.49
     but
    0.49
    <bos>
    0.47
    щото
    0.47
    <eos>
    0.47
     ↑
    0.46
    ,
    0.46
    tos
    0.46
    Activations Density 0.023%

    No Known Activations