Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11285
    Prev
    Next
    INDEX
    Explanations

    arm

    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
     arms
    -0.89
     arm
    -0.82
     Arms
    -0.82
    arms
    -0.76
    Arms
    -0.74
     ARMS
    -0.70
    antaranya
    -0.60
    arm
    -0.60
    Arm
    -0.52
     Arm
    -0.51
    POSITIVE LOGITS
     Folders
    0.61
     []:
    0.59
     folders
    0.57
    folder
    0.56
     folder
    0.55
    日閲覧
    0.55
    rrggbb
    0.55
     fett
    0.54
    enderror
    0.54
     Paso
    0.52
    Activations Density 0.007%

    No Known Activations