© 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. 4-CLT-HP
    4. 4533
    Prev
    Next
    INDEX
    Explanations

    Baltimore

    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
     &___
    -0.60
    Jeografia
    -0.59
     Exacts
    -0.53
    -|-
    -0.51
     Lighthouse
    -0.48
    لمانيا
    -0.48
     chi̍t
    -0.48
     berättar
    -0.48
    তথ্যসূত্র
    -0.47
    claro
    -0.47
    POSITIVE LOGITS
    ADU
    0.55
    adu
    0.55
    adat
    0.55
    VIAF
    0.54
    AD
    0.52
     adu
    0.51
    ad
    0.50
    adin
    0.49
    adto
    0.49
    udit
    0.48
    Activations Density 0.001%

    No Known Activations