© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44135
    Prev
    Next
    INDEX
    Explanations

    action

    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
     action
    -1.71
     Action
    -1.62
    Action
    -1.58
    action
    -1.55
     ACTION
    -1.43
    ACTION
    -1.32
     actions
    -1.22
     Actions
    -1.19
    actions
    -1.17
    Actions
    -1.13
    POSITIVE LOGITS
    OGND
    0.91
     MonoBehaviour
    0.82
     متعلقه
    0.77
     intptr
    0.76
    enumi
    0.74
    脚注の使い方
    0.74
     صوتيه
    0.71
    bolista
    0.68
    yntaxException
    0.67
     protoimpl
    0.66
    Activations Density 0.144%

    No Known Activations