© 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. 4-CLT-HP
    7. 4468
    Prev
    Next
    INDEX
    Explanations

    hydrochloric

    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
    EP
    -0.54
    mp
    -0.54
    AB
    -0.52
     Somers
    -0.50
    ep
    -0.50
     exp
    -0.49
     MP
    -0.47
     tomba
    -0.47
     condens
    -0.47
    mpy
    -0.46
    POSITIVE LOGITS
    ExtendWith
    0.58
     biografi
    0.55
    omock
    0.51
    bardier
    0.51
     חיצוניים
    0.50
     Normdatei
    0.48
     Dernière
    0.48
    坞
    0.47
    giphy
    0.47
     ég
    0.46
    Activations Density 0.004%

    No Known Activations