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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2847
    Prev
    Next
    INDEX
    Explanations

    into

    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
    rungsseite
    -0.68
     NUKAT
    -0.62
    Personendaten
    -0.58
    anyahu
    -0.56
    شهاد
    -0.54
    experts
    -0.53
    ArgsConstructor
    -0.51
    capace
    -0.50
    Datuak
    -0.50
    Hentet
    -0.49
    POSITIVE LOGITS
     going
    0.69
     it
    0.62
    <bos>
    0.60
     signing
    0.59
     doing
    0.59
     nakalista
    0.59
     buying
    0.57
     following
    0.54
     giving
    0.54
     taking
    0.54
    Activations Density 0.001%

    No Known Activations