© 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. 38940
    Prev
    Next
    INDEX
    Explanations

    the

    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
     the
    -0.91
     a
    -0.49
    the
    -0.48
     them
    -0.45
     grecque
    -0.44
     those
    -0.42
     interessanti
    -0.42
    :
    -0.42
     strumenti
    -0.41
    aspetto
    -0.40
    POSITIVE LOGITS
    Personendaten
    1.05
    TagMode
    1.00
    rungsseite
    0.97
     snippetHide
    0.96
    Tikang
    0.94
    featureID
    0.90
    NameInMap
    0.89
    TypedDataSet
    0.88
    homonymie
    0.86
    Rüyada
    0.85
    Activations Density 0.174%

    No Known Activations