© 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. 1067
    Prev
    Next
    INDEX
    Explanations

    ody

    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
     abuse
    -0.83
     Abuse
    -0.71
    ides
    -0.62
     abusive
    -0.54
    ody
    -0.51
    صد
    -0.51
     dent
    -0.50
     net
    -0.50
     cle
    -0.50
    telen
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    1.07
     kaarangay
    0.94
     resourceCulture
    0.90
    XmlAccessType
    0.90
     '\\;'
    0.89
    InjectAttribute
    0.89
    SourceChecksum
    0.88
    ConstraintMaker
    0.85
    ]")]
    0.83
    oredCriteria
    0.83
    Activations Density 0.048%

    No Known Activations