© 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. 1-CLT-HP
    7. 45580
    Prev
    Next
    INDEX
    Explanations

    erstein

    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
    erstein
    -0.75
     stället
    -0.68
     Aerop
    -0.65
     vägen
    -0.63
     sleepers
    -0.60
     itſelf
    -0.57
     Cliffs
    -0.56
     myſelf
    -0.55
    koľ
    -0.55
     Houſe
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.66
     nahilalakip
    0.65
    Personensuche
    0.65
    клопе
    0.63
    bit
    0.56
    ring
    0.55
    rise
    0.54
    Geplaatst
    0.52
    OGND
    0.52
    发表于
    0.51
    Activations Density 0.015%

    No Known Activations