© 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. 4-CLT-HP
    7. 4575
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    enumi
    -0.52
    
    -0.50
    contentPane
    -0.50
    ########.
    -0.49
     कैसी
    -0.48
     Gutes
    -0.48
    чайно
    -0.47
    upol
    -0.47
    љи
    -0.46
    mstyle
    -0.45
    POSITIVE LOGITS
     Roskov
    0.59
     Signalez
    0.56
    ūsų
    0.55
    jekk
    0.55
     getopt
    0.55
    <bos>
    0.53
     oiseaux
    0.52
     arvio
    0.52
    Personendaten
    0.51
    Према
    0.50
    Activations Density 0.005%

    No Known Activations