© 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. 20-CLT-HP
    7. 74588
    Prev
    Next
    INDEX
    Explanations

    Descriptions/Actions

    np_max-act-logits · 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
    StringVar
    -0.50
     strconv
    -0.47
    FormTagHelper
    -0.44
    XmlAccessorType
    -0.44
    '][$
    -0.42
    }();
    -0.42
    preuve
    -0.41
    uminense
    -0.40
     croire
    -0.40
    EK
    -0.39
    POSITIVE LOGITS
     nice
    0.71
     nicer
    0.63
     favorites
    0.61
     NICE
    0.60
    protoc
    0.59
     nicely
    0.57
     defense
    0.55
     hObject
    0.55
     ProtoMessage
    0.55
    Dichloropropane
    0.54
    Activations Density 0.001%

    No Known Activations