© 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. 1-CLT-HP
    7. 12135
    Prev
    Next
    INDEX
    Explanations

    alloon

    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
    fuls
    -1.45
     OSA
    -0.87
    alloon
    -0.81
    reactive
    -0.59
     sério
    -0.57
    GEBURTSDATUM
    -0.56
     cantit
    -0.56
    phoria
    -0.55
    sstil
    -0.53
     pancake
    -0.53
    POSITIVE LOGITS
    forKey
    0.57
     lenker
    0.56
    esModule
    0.51
     שוליים
    0.49
    tvguidetime
    0.48
    клопе
    0.47
    protoimpl
    0.47
    łaj
    0.44
    asible
    0.44
    cnia
    0.44
    Activations Density 0.117%

    No Known Activations