© 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. 4-CLT-HP
    7. 3399
    Prev
    Next
    INDEX
    Explanations

    Increases and decreases

    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
     propter
    -0.56
    decrease
    -0.54
    Decrease
    -0.53
     decrease
    -0.50
    दि
    -0.47
     jadx
    -0.47
     augmente
    -0.47
     decreased
    -0.47
     increase
    -0.47
     decreasing
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.65
    complexContent
    0.61
    libft
    0.60
    <?>
    0.58
    XmlAccessType
    0.58
    principalTable
    0.57
     Normdatei
    0.56
    </tfoot>
    0.55
    oa̍t
    0.55
    وبی
    0.55
    Activations Density 0.044%

    No Known Activations