© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13461
    Prev
    Next
    INDEX
    Explanations

    issues

    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
    gonic
    -0.83
     Efq
    -0.79
    OGND
    -0.77
     tartalomajánló
    -0.76
    #+#
    -0.75
     myſelf
    -0.74
    uxxxx
    -0.73
     doubtnut
    -0.73
    PhysRevD
    -0.73
    AndEndTag
    -0.72
    POSITIVE LOGITS
     like
    0.47
    tr
    0.45
    x
    0.44
     Depression
    0.43
    bon
    0.42
     building
    0.42
     gyhoeddwyd
    0.41
     old
    0.41
    ibase
    0.41
    inter
    0.40
    Activations Density 0.010%

    No Known Activations