© 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. 44116
    Prev
    Next
    INDEX
    Explanations

    this

    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
     söyl
    -0.68
     mitochond
    -0.58
     scalars
    -0.58
     eccl
    -0.57
     þat
    -0.56
     cohomology
    -0.56
     Gegend
    -0.55
    argli
    -0.55
     prosecution
    -0.54
     ſon
    -0.53
    POSITIVE LOGITS
    rungsseite
    0.84
     the
    0.67
    tagHelperRunner
    0.66
     TestBed
    0.61
    ]");
    0.60
    =$((
    0.59
    WriteTagHelper
    0.58
    ]='\
    0.56
    />";
    0.56
     resourceCulture
    0.55
    Activations Density 0.212%

    No Known Activations