© 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. 5-CLT-HP
    7. 96135
    Prev
    Next
    INDEX
    Explanations

    scholarly texts

    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
    yntaxException
    -0.61
     noDo
    -0.55
    Personensuche
    -0.53
     виправивши
    -0.52
     considérons
    -0.52
     onAnimation
    -0.50
    resizingMask
    -0.50
    ỡng
    -0.49
    Bronnen
    -0.49
    SOUNDBITE
    -0.49
    POSITIVE LOGITS
     of
    0.67
     specializing
    0.55
     and
    0.54
    writing
    0.50
    UnusedPrivate
    0.50
     GetEnumerator
    0.49
    shadowOffset
    0.49
    IonicModule
    0.47
    stiff
    0.47
     specialized
    0.47
    Activations Density 0.000%

    No Known Activations