© 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. 1-CLT-HP
    7. 13187
    Prev
    Next
    INDEX
    Explanations

    another

    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
     mergeFrom
    -0.64
    BeginInit
    -0.58
     ComVisible
    -0.53
     AssemblyCulture
    -0.49
    ?,?,
    -0.48
     resourceCulture
    -0.48
    inyin
    -0.47
    glades
    -0.47
    StructEnd
    -0.47
     Numerade
    -0.46
    POSITIVE LOGITS
    featureID
    0.59
    Effort
    0.57
     and
    0.57
    posedge
    0.50
    enterOuterAlt
    0.50
    Життєпис
    0.50
     Cæsar
    0.50
     createState
    0.49
    editor
    0.49
    RetentionPolicy
    0.48
    Activations Density 0.001%

    No Known Activations