© 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. 1060
    Prev
    Next
    INDEX
    Explanations

    weathered

    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
    iel
    -1.30
    zzar
    -1.13
    IEL
    -0.52
    iela
    -0.50
    Seni
    -0.49
    el
    -0.49
    iels
    -0.48
    na
    -0.46
    TestingModule
    -0.46
    ANDA
    -0.46
    POSITIVE LOGITS
    Rhestr
    0.73
    tvguidetime
    0.71
     Efq
    0.67
    aneously
    0.65
     Diſ
    0.65
     ་་
    0.64
    theless
    0.64
    tonsoft
    0.63
    wiſe
    0.63
     Conſ
    0.63
    Activations Density 1.653%

    No Known Activations