© 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. 91092
    Prev
    Next
    INDEX
    Explanations

    technical/scientific document

    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
    <h4>
    -0.54
    γγε
    -0.49
     Roskov
    -0.45
    acak
    -0.45
    DataSnapshot
    -0.45
     and
    -0.45
     linkovi
    -0.45
    stalgia
    -0.44
    subsubsection
    -0.44
     становника
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.73
    Portail
    0.71
    SequentialGroup
    0.66
     distanciation
    0.62
    glEnd
    0.61
     ComVisible
    0.59
    odori
    0.59
    URLException
    0.59
    ChildIndex
    0.58
     Clu
    0.57
    Activations Density 0.163%

    No Known Activations