© 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. 43997
    Prev
    Next
    INDEX
    Explanations

    ie

    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
     الحره
    -0.84
    Yet
    -0.76
     Yet
    -0.74
     bicarbonate
    -0.71
    最快更新
    -0.69
    хьтан
    -0.66
    Rujuakan
    -0.66
    saraba
    -0.63
    ionario
    -0.63
    Portale
    -0.58
    POSITIVE LOGITS
    ,
    0.72
     besides
    0.54
     as
    0.53
     Zitron
    0.53
     further
    0.52
     again
    0.52
     after
    0.50
     aside
    0.50
    SuccessListener
    0.50
     somehow
    0.49
    Activations Density 1.748%

    No Known Activations