© 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. 38888
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    MessageTagHelper
    -0.76
    StoryboardSegue
    -0.75
    findpost
    -0.74
    ########.
    -0.65
    Izvori
    -0.63
     snippetHide
    -0.63
     समीक्षक
    -0.63
     ivelany
    -0.62
    featureID
    -0.62
     Walkover
    -0.60
    POSITIVE LOGITS
     tob
    0.60
     الوطنيه
    0.57
    pulumi
    0.56
    suke
    0.55
     myſelf
    0.53
     obst
    0.53
     Cuckoo
    0.52
     cottages
    0.52
     Declarations
    0.52
    сії
    0.51
    Activations Density 0.354%

    No Known Activations