© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93636
    Prev
    Next
    INDEX
    Explanations

    interview

    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
     interview
    -1.42
    Personendaten
    -1.42
     Interview
    -1.38
    interview
    -1.38
    findpost
    -1.29
    Interview
    -1.26
     interviewer
    -1.25
    Personensuche
    -1.25
    featureID
    -1.23
     INTERVIEW
    -1.23
    POSITIVE LOGITS
    .
    0.59
    ↵↵
    0.55
    ,
    0.55
     with
    0.54
     and
    0.52
     (
    0.52
    1
    0.52
     
    0.49
    4
    0.49
    2
    0.49
    Activations Density 0.094%

    No Known Activations