Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1578
    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
    .
    -0.48
    C
    -0.42
     followed
    -0.42
    x
    -0.41
    !
    -0.38
    M
    -0.37
    <bos>
    -0.36
    V
    -0.35
    H
    -0.35
    2
    -0.34
    POSITIVE LOGITS
     ExecuteAsync
    1.21
     autorytatywna
    1.12
    NUMX
    1.06
    __(/*!
    1.03
    )++;
    1.02
    ]")]
    0.97
    ^(@)
    0.97
     disambiguazione
    0.95
     AssemblyTitle
    0.91
    SharedDtor
    0.90
    Activations Density 0.002%

    No Known Activations