© 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. 5-CLT-HP
    7. 95060
    Prev
    Next
    INDEX
    Explanations

    methods or explanations

    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
    AddTagHelper
    -0.74
     utafitiHapana
    -0.65
    abestanden
    -0.65
     itſelf
    -0.60
    sidemargin
    -0.59
    nachron
    -0.58
    évaluateur
    -0.57
    ();)
    -0.56
    sizePolicy
    -0.55
    édrale
    -0.54
    POSITIVE LOGITS
     all
    0.69
     do
    0.64
     haven
    0.63
     toutes
    0.59
     don
    0.58
    都
    0.57
     semuanya
    0.56
     đều
    0.56
     tend
    0.56
     usually
    0.55
    Activations Density 0.004%

    No Known Activations